Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +26 -26
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
README.md
CHANGED
@@ -10,7 +10,7 @@ model-index:
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
-
value:
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 276.30 +/- 20.40
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7efe4b5c05f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efe4b5c0680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efe4b5c0710>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efe4b5c07a0>", "_build": "<function ActorCriticPolicy._build at 0x7efe4b5c0830>", "forward": "<function ActorCriticPolicy.forward at 0x7efe4b5c08c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efe4b5c0950>", "_predict": "<function ActorCriticPolicy._predict at 0x7efe4b5c09e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efe4b5c0a70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efe4b5c0b00>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efe4b5c0b90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7efe4b6122d0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651762018.1948504, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7fc540b425f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc540b42680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc540b42710>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc540b427a0>", "_build": "<function ActorCriticPolicy._build at 0x7fc540b42830>", "forward": "<function ActorCriticPolicy.forward at 0x7fc540b428c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc540b42950>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc540b429e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc540b42a70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc540b42b00>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc540b42b90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fc540b92600>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 2506752, "_total_timesteps": 2500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1653162705.981662, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0027007999999999477, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 612, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b438adf9e0825ecbb8dea9466ae1eaf2cb193ce15ff8b41484f87d7d709d693c
|
3 |
+
size 144094
|
ppo-LunarLander-v2/data
CHANGED
@@ -1,28 +1,28 @@
|
|
1 |
{
|
2 |
"policy_class": {
|
3 |
":type:": "<class 'abc.ABCMeta'>",
|
4 |
-
":serialized:": "
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
-
"_abc_impl": "<_abc_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
-
":serialized:": "
|
26 |
"dtype": "float32",
|
27 |
"_shape": [
|
28 |
8
|
@@ -35,47 +35,47 @@
|
|
35 |
},
|
36 |
"action_space": {
|
37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
-
":serialized:": "
|
39 |
"n": 4,
|
40 |
"_shape": [],
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
-
"num_timesteps":
|
46 |
-
"_total_timesteps":
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
-
"start_time":
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
-
":serialized:": "
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
-
":serialized:": "
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining": -0.
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
-
":serialized:": "
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
@@ -86,7 +86,7 @@
|
|
86 |
"n_epochs": 4,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
-
":serialized:": "
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
|
|
1 |
{
|
2 |
"policy_class": {
|
3 |
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7fc540b425f0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc540b42680>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc540b42710>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc540b427a0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fc540b42830>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fc540b428c0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc540b42950>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fc540b429e0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc540b42a70>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc540b42b00>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc540b42b90>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fc540b92600>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
"dtype": "float32",
|
27 |
"_shape": [
|
28 |
8
|
|
|
35 |
},
|
36 |
"action_space": {
|
37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
"n": 4,
|
40 |
"_shape": [],
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 2506752,
|
46 |
+
"_total_timesteps": 2500000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1653162705.981662,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.0027007999999999477,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 612,
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
|
|
86 |
"n_epochs": 4,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a3f6dea2de87ba6577964c7bb795537c0bd365f04ad3e33881bf171ccfb0b5d
|
3 |
+
size 84893
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43201
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e20b1bc57a1b66bc7dca7a0c5cf5c63448d4dee5d368602286a35b22848319e1
|
3 |
size 43201
|
replay.mp4
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e74322b35c34b3dc59c373e3e350307cf866388ddb8e163c0b1fea777d00fa49
|
3 |
+
size 192745
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 276.2959377390479, "std_reward": 20.398451550247543, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-21T20:28:36.192386"}
|