second commit

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfd24325cfd9889d7f930ea4eeb870ff83361f4e0b360f6de7108c741104e8f5
-size 1417437
+oid sha256:5b3f076df2e3b8cbec9311b2b8827eb264334f587a1e5e315340235b9057f583
+size 2468409

Pyramids/Pyramids-2000103.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b3f076df2e3b8cbec9311b2b8827eb264334f587a1e5e315340235b9057f583
+size 2468409

Pyramids/Pyramids-2000103.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cedb7d72a892b9a39494684cea6e039b16185d48ce77bfd1e9b7715c7000a3f4
+size 14960218

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902e50e371c2056e3cf44262e9c2e04a37383a2fe825f424d91ca9af4841fca6
-size 8652382
+oid sha256:cedb7d72a892b9a39494684cea6e039b16185d48ce77bfd1e9b7715c7000a3f4
+size 14960218

Pyramids/{events.out.tfevents.1673856684.c9c677f41b73.22727.0 → events.out.tfevents.1673859769.c9c677f41b73.35572.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7f855e0ce711ad04b63261101d8dabeee63926193453ed49e4705eb7aa5345f
-size 191527
+oid sha256:88e1615cf04dbe34b94ba7e8da548408fc4fa27409663a070bf4c2dde6d23677
+size 627988

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 1, "checkpoint_interval": 500000, "max_steps": 2000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -16,7 +16,7 @@ behaviors:
     network_settings:
       normalize: false
       hidden_units: 512
-      num_layers: 2
+      num_layers: 3
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
@@ -47,9 +47,9 @@ behaviors:
         learning_rate: 0.0001
         encoding_size: null
     init_path: null
-    keep_checkpoints: 5
+    keep_checkpoints: 1
     checkpoint_interval: 500000
-    max_steps: 1000000
+    max_steps: 2000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -79,7 +79,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55091 [Flags] 2 [Guid] 54601149 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.2 [Port] 55025 [Flags] 2 [Guid] 430108206 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.086 seconds
+- Completed reload, in  0.082 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -68,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.761808 ms
+UnloadTime: 0.761957 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 13716 frames, [32.0 KB-64.0 KB]: 4173 frames, [64.0 KB-128.0 KB]: 874 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3034 frames, [32.0 KB-64.0 KB]: 24542 frames, [64.0 KB-128.0 KB]: 9947 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -126,7 +123,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -136,7 +133,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -186,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18465 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37225 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12016
+  Peak main deferred allocation count 12170
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18763 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37523 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.2 MB
+      Peak Allocated memory 29.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18764 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37524 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.9 MB
+      Peak Allocated memory 23.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18763 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37523 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 18764 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 37524 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,13 +272,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18465 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 37225 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 18763 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 37523 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -293,19 +290,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18764 frames
+      Peak usage frame count: [0-1.0 KB]: 37524 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 18764 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37524 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 18764 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 37524 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -314,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673858381820,"processId":22748,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673864378162,"processId":35589,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,256 +2,256 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.01766229420900345,
-            "min": 0.016413062810897827,
-            "max": 1.4064217805862427,
-            "count": 33
+            "value": 0.17564757168293,
+            "min": 0.17199935019016266,
+            "max": 1.412055253982544,
+            "count": 66
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 529.0210571289062,
-            "min": 490.0284118652344,
-            "max": 42665.2109375,
-            "count": 33
+            "value": 5235.70263671875,
+            "min": 5159.98046875,
+            "max": 42836.109375,
+            "count": 66
         },
         "Pyramids.Step.mean": {
-            "value": 989993.0,
-            "min": 29975.0,
-            "max": 989993.0,
-            "count": 33
+            "value": 1979962.0,
+            "min": 29895.0,
+            "max": 1979962.0,
+            "count": 66
         },
         "Pyramids.Step.sum": {
-            "value": 989993.0,
-            "min": 29975.0,
-            "max": 989993.0,
-            "count": 33
+            "value": 1979962.0,
+            "min": 29895.0,
+            "max": 1979962.0,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.09685161709785461,
-            "min": -0.10567724704742432,
-            "max": -0.04549936205148697,
-            "count": 33
+            "value": 0.7302473783493042,
+            "min": -0.08650728315114975,
+            "max": 0.8179190158843994,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -23.244388580322266,
-            "min": -25.468215942382812,
-            "max": -11.056344985961914,
-            "count": 33
+            "value": 209.58099365234375,
+            "min": -20.848255157470703,
+            "max": 248.6473846435547,
+            "count": 66
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.4389577805995941,
-            "min": 0.4055100381374359,
-            "max": 0.4869409501552582,
-            "count": 33
+            "value": 0.0018236269243061543,
+            "min": -0.013203675858676434,
+            "max": 0.2915990650653839,
+            "count": 66
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 105.34986877441406,
-            "min": 98.5389404296875,
-            "max": 117.35276794433594,
-            "count": 33
+            "value": 0.5233809351921082,
+            "min": -3.9875102043151855,
+            "max": 70.27537536621094,
+            "count": 66
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06463740351322923,
-            "min": 0.0640608792372159,
-            "max": 0.07272620832427881,
-            "count": 33
+            "value": 0.06963876409110312,
+            "min": 0.06497480453219309,
+            "max": 0.07521226492166487,
+            "count": 66
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9049236491852093,
-            "min": 0.5090834582699517,
-            "max": 1.009000846796313,
-            "count": 33
+            "value": 0.9749426972754436,
+            "min": 0.49167414049379765,
+            "max": 1.0622349602453336,
+            "count": 66
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.000723538274395592,
-            "min": 0.00015797421243176683,
-            "max": 0.014893088642434577,
-            "count": 33
+            "value": 0.017084497623931466,
+            "min": 0.000786096035043501,
+            "max": 0.017084497623931466,
+            "count": 66
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.010129535841538287,
-            "min": 0.0020536647616129686,
-            "max": 0.10425162049704204,
-            "count": 33
+            "value": 0.23918296673504053,
+            "min": 0.011005344490609014,
+            "max": 0.23918296673504053,
+            "count": 66
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.681147439649997e-06,
-            "min": 7.681147439649997e-06,
-            "max": 0.00029523741587324286,
-            "count": 33
+            "value": 5.377641064628573e-06,
+            "min": 5.377641064628573e-06,
+            "max": 0.0002975753150939428,
+            "count": 66
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010753606415509996,
-            "min": 0.00010753606415509996,
-            "max": 0.0036330169889943996,
-            "count": 33
+            "value": 7.528697490480002e-05,
+            "min": 7.528697490480002e-05,
+            "max": 0.0039800220733259995,
+            "count": 66
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10256035000000001,
-            "min": 0.10256035000000001,
-            "max": 0.1984124714285714,
-            "count": 33
+            "value": 0.1017925142857143,
+            "min": 0.1017925142857143,
+            "max": 0.19919177142857142,
+            "count": 66
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4358449000000002,
-            "min": 1.3888873,
-            "max": 2.6110056,
-            "count": 33
+            "value": 1.4250952000000001,
+            "min": 1.3943424,
+            "max": 2.726674,
+            "count": 66
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002657789649999999,
-            "min": 0.0002657789649999999,
-            "max": 0.009841405895714287,
-            "count": 33
+            "value": 0.00018907217714285722,
+            "min": 0.00018907217714285722,
+            "max": 0.009919257965714285,
+            "count": 66
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0037209055099999984,
-            "min": 0.0037209055099999984,
-            "max": 0.12111945944,
-            "count": 33
+            "value": 0.002647010480000001,
+            "min": 0.002647010480000001,
+            "max": 0.13267473259999998,
+            "count": 66
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.428443044424057,
-            "min": 0.37398988008499146,
-            "max": 0.6795439124107361,
-            "count": 33
+            "value": 0.007750507909804583,
+            "min": 0.0077226245775818825,
+            "max": 0.45741453766822815,
+            "count": 66
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 5.998202800750732,
-            "min": 4.124783039093018,
-            "max": 6.3132500648498535,
-            "count": 33
+            "value": 0.10850711166858673,
+            "min": 0.1081167459487915,
+            "max": 3.20190167427063,
+            "count": 66
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 973.6333333333333,
-            "min": 941.40625,
-            "max": 999.0,
-            "count": 33
+            "value": 251.01666666666668,
+            "min": 217.61029411764707,
+            "max": 997.6451612903226,
+            "count": 66
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29209.0,
-            "min": 16646.0,
-            "max": 32387.0,
-            "count": 33
+            "value": 30122.0,
+            "min": 16822.0,
+            "max": 33923.0,
+            "count": 66
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.9075200490653514,
-            "min": -0.9998194060979351,
-            "max": -0.5671187972184271,
-            "count": 33
+            "value": 1.715639984048903,
+            "min": -0.9340839227361064,
+            "max": 1.7820962852901883,
+            "count": 66
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -27.225601471960545,
-            "min": -31.99360164999962,
-            "max": -14.662000820040703,
-            "count": 33
+            "value": 205.87679808586836,
+            "min": -28.956601604819298,
+            "max": 240.58299851417542,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.9075200490653514,
-            "min": -0.9998194060979351,
-            "max": -0.5671187972184271,
-            "count": 33
+            "value": 1.715639984048903,
+            "min": -0.9340839227361064,
+            "max": 1.7820962852901883,
+            "count": 66
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -27.225601471960545,
-            "min": -31.99360164999962,
-            "max": -14.662000820040703,
-            "count": 33
+            "value": 205.87679808586836,
+            "min": -28.956601604819298,
+            "max": 240.58299851417542,
+            "count": 66
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 4.155332256356875,
-            "min": 3.6240612815189013,
-            "max": 12.94854290169828,
-            "count": 33
+            "value": 0.020352095427794363,
+            "min": 0.018926001367745575,
+            "max": 8.121869025861516,
+            "count": 66
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 124.65996769070625,
-            "min": 97.46026045084,
-            "max": 220.12522932887077,
-            "count": 33
+            "value": 2.4422514513353235,
+            "min": 2.3590088674100116,
+            "max": 138.07177343964577,
+            "count": 66
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 66
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 66
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673856681",
+        "start_time_seconds": "1673859766",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1673858381"
+        "end_time_seconds": "1673864378"
     },
-    "total": 1700.7824041660006,
+    "total": 4612.17017888,
     "count": 1,
-    "self": 0.43527119400096126,
+    "self": 0.636505007998494,
     "children": {
         "run_training.setup": {
-            "total": 0.11136462400008895,
+            "total": 0.10362446600083786,
             "count": 1,
-            "self": 0.11136462400008895
+            "self": 0.10362446600083786
         },
         "TrainerController.start_learning": {
-            "total": 1700.2357683479995,
+            "total": 4611.430049406001,
             "count": 1,
-            "self": 1.1601813179750025,
+            "self": 2.6749275399597536,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.325825495000572,
+                    "total": 6.263961189000838,
                     "count": 1,
-                    "self": 6.325825495000572
+                    "self": 6.263961189000838
                 },
                 "TrainerController.advance": {
-                    "total": 1692.655590934025,
-                    "count": 62945,
-                    "self": 1.235487172082685,
+                    "total": 4602.35655740304,
+                    "count": 129580,
+                    "self": 2.676332468941837,
                     "children": {
                         "env_step": {
-                            "total": 1033.2554563730473,
-                            "count": 62945,
-                            "self": 931.6410963988046,
+                            "total": 3230.596781056165,
+                            "count": 129580,
+                            "self": 3009.8477219878932,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 100.88433462003286,
-                                    "count": 62945,
-                                    "self": 4.058513438098089,
+                                    "total": 219.1618188794364,
+                                    "count": 129580,
+                                    "self": 8.642878000473502,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 96.82582118193477,
-                                            "count": 62544,
-                                            "self": 32.67217737797455,
+                                            "total": 210.5189408789629,
+                                            "count": 125077,
+                                            "self": 67.54842344763347,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 64.15364380396022,
-                                                    "count": 62544,
-                                                    "self": 64.15364380396022
+                                                    "total": 142.97051743132943,
+                                                    "count": 125077,
+                                                    "self": 142.97051743132943
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.730025354209829,
-                                    "count": 62945,
+                                    "total": 1.5872401888354943,
+                                    "count": 129580,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1695.9519610519455,
-                                            "count": 62945,
+                                            "total": 4601.900233721275,
+                                            "count": 129580,
                                             "is_parallel": true,
-                                            "self": 859.4921320607582,
+                                            "self": 1792.186563642068,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0016580019992034067,
+                                                            "total": 0.0016839499985508155,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000597857999309781,
+                                                            "self": 0.0005945569973846432,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0010601439998936257,
+                                                                    "total": 0.0010893930011661723,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0010601439998936257
+                                                                    "self": 0.0010893930011661723
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.044470292999903904,
+                                                            "total": 0.04658760999882361,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005088029993203236,
+                                                            "self": 0.00047299099969677627,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004613780001818668,
+                                                                    "total": 0.0004753920002258383,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004613780001818668
+                                                                    "self": 0.0004753920002258383
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04191104300025472,
+                                                                    "total": 0.04406484199898841,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04191104300025472
+                                                                    "self": 0.04406484199898841
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001589069000146992,
+                                                                    "total": 0.0015743849999125814,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004122890013604774,
+                                                                    "self": 0.0004062549978698371,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0011767799987865146,
+                                                                            "total": 0.0011681300020427443,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0011767799987865146
+                                                                            "self": 0.0011681300020427443
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 836.4598289911874,
-                                                    "count": 62944,
+                                                    "total": 2809.713670079207,
+                                                    "count": 129579,
                                                     "is_parallel": true,
-                                                    "self": 27.310904872894753,
+                                                    "self": 56.21503635393492,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 22.24475964220437,
-                                                            "count": 62944,
+                                                            "total": 43.74424101002296,
+                                                            "count": 129579,
                                                             "is_parallel": true,
-                                                            "self": 22.24475964220437
+                                                            "self": 43.74424101002296
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 689.8779451850542,
-                                                            "count": 62944,
+                                                            "total": 2506.5505088333703,
+                                                            "count": 129579,
                                                             "is_parallel": true,
-                                                            "self": 689.8779451850542
+                                                            "self": 2506.5505088333703
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 97.02621929103407,
-                                                            "count": 62944,
+                                                            "total": 203.20388388187894,
+                                                            "count": 129579,
                                                             "is_parallel": true,
-                                                            "self": 20.978126786360008,
+                                                            "self": 44.664562637542986,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 76.04809250467406,
-                                                                    "count": 503552,
+                                                                    "total": 158.53932124433595,
+                                                                    "count": 1036632,
                                                                     "is_parallel": true,
-                                                                    "self": 76.04809250467406
+                                                                    "self": 158.53932124433595
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 658.164647388895,
-                            "count": 62945,
-                            "self": 1.9371244678804942,
+                            "total": 1369.083443877933,
+                            "count": 129580,
+                            "self": 5.22346910975466,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 139.1224653950194,
-                                    "count": 62945,
-                                    "self": 138.9328996990198,
+                                    "total": 295.9780959271702,
+                                    "count": 129580,
+                                    "self": 295.441841344169,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.1895656959995904,
-                                            "count": 2,
-                                            "self": 0.1895656959995904
+                                            "total": 0.5362545830012095,
+                                            "count": 4,
+                                            "self": 0.5362545830012095
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 517.1050575259951,
-                                    "count": 436,
-                                    "self": 201.26040637295046,
+                                    "total": 1067.881878841008,
+                                    "count": 930,
+                                    "self": 395.43516538512085,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 315.84465115304465,
-                                            "count": 22803,
-                                            "self": 315.84465115304465
+                                            "total": 672.4467134558872,
+                                            "count": 45546,
+                                            "self": 672.4467134558872
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.309997039963491e-07,
+                    "total": 9.800005500437692e-07,
                     "count": 1,
-                    "self": 9.309997039963491e-07
+                    "self": 9.800005500437692e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09416966999924625,
+                    "total": 0.13460229399970558,
                     "count": 1,
-                    "self": 0.0014965779992053285,
+                    "self": 0.0027112980005767895,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09267309200004092,
+                            "total": 0.1318909959991288,
                             "count": 1,
-                            "self": 0.09267309200004092
+                            "self": 0.1318909959991288
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,22 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499915,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499915.onnx",
-                "reward": null,
-                "creation_time": 1673857554.1033096,
+                "steps": 2000103,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2000103.onnx",
+                "reward": 1.5759999801715214,
+                "creation_time": 1673864377.6135306,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499915.pt"
-                ]
-            },
-            {
-                "steps": 999913,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999913.onnx",
-                "reward": null,
-                "creation_time": 1673858381.3184521,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999913.pt"
-                ]
-            },
-            {
-                "steps": 1000041,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000041.onnx",
-                "reward": null,
-                "creation_time": 1673858381.4262464,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000041.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2000103.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000041,
+            "steps": 2000103,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1673858381.4262464,
+            "reward": 1.5759999801715214,
+            "creation_time": 1673864377.6135306,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000041.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-2000103.pt"
             ]
         }
     },