Done
Browse files- README.md +1 -1
- config.json +1 -1
- ppo_model_marina.zip +2 -2
- ppo_model_marina/data +47 -39
- ppo_model_marina/policy.optimizer.pth +2 -2
- ppo_model_marina/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
|
@@ -16,7 +16,7 @@ model-index:
|
|
| 16 |
type: LunarLander-v2
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
-
value:
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
|
|
|
| 16 |
type: LunarLander-v2
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
+
value: 296.22 +/- 14.37
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "
|
|
|
|
| 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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7ff9b85e1240>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff9b85e12d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff9b85e1360>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff9b85e13f0>", "_build": "<function ActorCriticPolicy._build at 0x7ff9b85e1480>", "forward": "<function ActorCriticPolicy.forward at 0x7ff9b85e1510>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff9b85e15a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff9b85e1630>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff9b85e16c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff9b85e1750>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff9b85e17e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff9b85e1870>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff9b85d7140>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 100, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1690199650549036425, "learning_rate": 0.0, "tensorboard_log": null, "_last_obs": null, "_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": -7.935999999997279e-05, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 24416, "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:": "gAWVxwEAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUtDQwRkAVMAlE5HAAAAAAAAAACGlCmMAV+UhZSMIDxpcHl0aG9uLWlucHV0LTEyOS02ZTc1ZGVjN2IwZjY+lIwIPGxhbWJkYT6USwdDAgQAlCkpdJRSlH2UKIwLX19wYWNrYWdlX1+UTowIX19uYW1lX1+UjAhfX21haW5fX5R1Tk5OdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgWfZR9lChoE2gNjAxfX3F1YWxuYW1lX1+UaA2MD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBSMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UTowXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.6", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo_model_marina.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:c26303182f0903df1792212a3cfffbe8d508cbbb4d2c82454c8817448365900d
|
| 3 |
+
size 140968
|
ppo_model_marina/data
CHANGED
|
@@ -1,36 +1,44 @@
|
|
| 1 |
{
|
| 2 |
"policy_class": {
|
| 3 |
":type:": "<class 'abc.ABCMeta'>",
|
| 4 |
-
":serialized:": "
|
| 5 |
-
"__module__": "
|
| 6 |
-
"
|
| 7 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"__abstractmethods__": "frozenset()",
|
| 9 |
-
"_abc_impl": "<_abc._abc_data object at
|
| 10 |
},
|
| 11 |
"verbose": 1,
|
| 12 |
"policy_kwargs": {},
|
| 13 |
-
"num_timesteps":
|
| 14 |
-
"_total_timesteps":
|
| 15 |
"_num_timesteps_at_start": 0,
|
| 16 |
"seed": null,
|
| 17 |
"action_noise": null,
|
| 18 |
-
"start_time":
|
| 19 |
-
"learning_rate": 0.
|
| 20 |
"tensorboard_log": null,
|
| 21 |
-
"_last_obs":
|
| 22 |
-
":type:": "<class 'numpy.ndarray'>",
|
| 23 |
-
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADO1lDzbu6o+yumGu8eWib6aJyQ9s6DuPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
| 24 |
-
},
|
| 25 |
"_last_episode_starts": {
|
| 26 |
":type:": "<class 'numpy.ndarray'>",
|
| 27 |
-
":serialized:": "
|
| 28 |
},
|
| 29 |
"_last_original_obs": null,
|
| 30 |
"_episode_num": 0,
|
| 31 |
"use_sde": false,
|
| 32 |
"sde_sample_freq": -1,
|
| 33 |
-
"_current_progress_remaining": -
|
| 34 |
"_stats_window_size": 100,
|
| 35 |
"ep_info_buffer": {
|
| 36 |
":type:": "<class 'collections.deque'>",
|
|
@@ -40,20 +48,35 @@
|
|
| 40 |
":type:": "<class 'collections.deque'>",
|
| 41 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
| 42 |
},
|
| 43 |
-
"_n_updates":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
"observation_space": {
|
| 45 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
| 46 |
-
":serialized:": "
|
| 47 |
"dtype": "float32",
|
| 48 |
-
"bounded_below": "[
|
| 49 |
-
"bounded_above": "[
|
| 50 |
"_shape": [
|
| 51 |
8
|
| 52 |
],
|
| 53 |
-
"low": "[-
|
| 54 |
-
"high": "[
|
| 55 |
-
"low_repr": "
|
| 56 |
-
"high_repr": "
|
| 57 |
"_np_random": null
|
| 58 |
},
|
| 59 |
"action_space": {
|
|
@@ -66,23 +89,8 @@
|
|
| 66 |
"_np_random": null
|
| 67 |
},
|
| 68 |
"n_envs": 1,
|
| 69 |
-
"n_steps": 2048,
|
| 70 |
-
"gamma": 0.99,
|
| 71 |
-
"gae_lambda": 0.95,
|
| 72 |
-
"ent_coef": 0.0,
|
| 73 |
-
"vf_coef": 0.5,
|
| 74 |
-
"max_grad_norm": 0.5,
|
| 75 |
-
"batch_size": 64,
|
| 76 |
-
"n_epochs": 10,
|
| 77 |
-
"clip_range": {
|
| 78 |
-
":type:": "<class 'function'>",
|
| 79 |
-
":serialized:": "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"
|
| 80 |
-
},
|
| 81 |
-
"clip_range_vf": null,
|
| 82 |
-
"normalize_advantage": true,
|
| 83 |
-
"target_kl": null,
|
| 84 |
"lr_schedule": {
|
| 85 |
":type:": "<class 'function'>",
|
| 86 |
-
":serialized:": "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
|
| 87 |
}
|
| 88 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"policy_class": {
|
| 3 |
":type:": "<class 'abc.ABCMeta'>",
|
| 4 |
+
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
| 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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7ff9b85e1240>",
|
| 8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff9b85e12d0>",
|
| 9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff9b85e1360>",
|
| 10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff9b85e13f0>",
|
| 11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7ff9b85e1480>",
|
| 12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7ff9b85e1510>",
|
| 13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff9b85e15a0>",
|
| 14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff9b85e1630>",
|
| 15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7ff9b85e16c0>",
|
| 16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff9b85e1750>",
|
| 17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff9b85e17e0>",
|
| 18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff9b85e1870>",
|
| 19 |
"__abstractmethods__": "frozenset()",
|
| 20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7ff9b85d7140>"
|
| 21 |
},
|
| 22 |
"verbose": 1,
|
| 23 |
"policy_kwargs": {},
|
| 24 |
+
"num_timesteps": 0,
|
| 25 |
+
"_total_timesteps": 100,
|
| 26 |
"_num_timesteps_at_start": 0,
|
| 27 |
"seed": null,
|
| 28 |
"action_noise": null,
|
| 29 |
+
"start_time": 1690199650549036425,
|
| 30 |
+
"learning_rate": 0.0,
|
| 31 |
"tensorboard_log": null,
|
| 32 |
+
"_last_obs": null,
|
|
|
|
|
|
|
|
|
|
| 33 |
"_last_episode_starts": {
|
| 34 |
":type:": "<class 'numpy.ndarray'>",
|
| 35 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
| 36 |
},
|
| 37 |
"_last_original_obs": null,
|
| 38 |
"_episode_num": 0,
|
| 39 |
"use_sde": false,
|
| 40 |
"sde_sample_freq": -1,
|
| 41 |
+
"_current_progress_remaining": -7.935999999997279e-05,
|
| 42 |
"_stats_window_size": 100,
|
| 43 |
"ep_info_buffer": {
|
| 44 |
":type:": "<class 'collections.deque'>",
|
|
|
|
| 48 |
":type:": "<class 'collections.deque'>",
|
| 49 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
| 50 |
},
|
| 51 |
+
"_n_updates": 24416,
|
| 52 |
+
"n_steps": 1024,
|
| 53 |
+
"gamma": 0.999,
|
| 54 |
+
"gae_lambda": 0.98,
|
| 55 |
+
"ent_coef": 0.01,
|
| 56 |
+
"vf_coef": 0.5,
|
| 57 |
+
"max_grad_norm": 0.5,
|
| 58 |
+
"batch_size": 64,
|
| 59 |
+
"n_epochs": 4,
|
| 60 |
+
"clip_range": {
|
| 61 |
+
":type:": "<class 'function'>",
|
| 62 |
+
":serialized:": "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"
|
| 63 |
+
},
|
| 64 |
+
"clip_range_vf": null,
|
| 65 |
+
"normalize_advantage": true,
|
| 66 |
+
"target_kl": null,
|
| 67 |
"observation_space": {
|
| 68 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
| 69 |
+
":serialized:": "gAWVyQEAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAAAAAAAAAAAAJRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAAAAAAAAAAAAJRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP+UaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjAQtaW5mlIwJaGlnaF9yZXBylIwDaW5mlIwKX25wX3JhbmRvbZROdWIu",
|
| 70 |
"dtype": "float32",
|
| 71 |
+
"bounded_below": "[False False False False False False False False]",
|
| 72 |
+
"bounded_above": "[False False False False False False False False]",
|
| 73 |
"_shape": [
|
| 74 |
8
|
| 75 |
],
|
| 76 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
| 77 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
| 78 |
+
"low_repr": "-inf",
|
| 79 |
+
"high_repr": "inf",
|
| 80 |
"_np_random": null
|
| 81 |
},
|
| 82 |
"action_space": {
|
|
|
|
| 89 |
"_np_random": null
|
| 90 |
},
|
| 91 |
"n_envs": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
"lr_schedule": {
|
| 93 |
":type:": "<class 'function'>",
|
| 94 |
+
":serialized:": "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"
|
| 95 |
}
|
| 96 |
}
|
ppo_model_marina/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:dcf4430c20c926f053a022a52515f66d0f575d210de28e2656fb11db5201c286
|
| 3 |
+
size 88057
|
ppo_model_marina/policy.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43329
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:806b6a009b301f1ffcd6b3caed2f475e223aa2a9dcddfed75e2b569f122e7b28
|
| 3 |
size 43329
|
replay.mp4
CHANGED
|
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward":
|
|
|
|
| 1 |
+
{"mean_reward": 296.22384029999995, "std_reward": 14.365343425309964, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-24T11:58:10.673809"}
|