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 +21 -21
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/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: 293.03 +/- 24.66
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
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 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 0x7bd01a7a3c70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7bd01a7a3d00>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7bd01a7a3d90>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7bd01a7a3e20>", "_build": "<function ActorCriticPolicy._build at 0x7bd01a7a3eb0>", "forward": "<function ActorCriticPolicy.forward at 0x7bd01a7a3f40>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7bd01a7ac040>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7bd01a7ac0d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7bd01a7ac160>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7bd01a7ac1f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7bd01a7ac280>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7bd01a7ac310>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7bd01a79b0c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 3014656, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1691067076280521037, "learning_rate": 0.0003, "tensorboard_log": null, "_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": -0.004885333333333408, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1472, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_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": 16, "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": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "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": "3.10.12", "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"}}
|
|
|
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 0x7ca94524a050>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ca94524a0e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ca94524a170>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ca94524a200>", "_build": "<function ActorCriticPolicy._build at 0x7ca94524a290>", "forward": "<function ActorCriticPolicy.forward at 0x7ca94524a320>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ca94524a3b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ca94524a440>", "_predict": "<function ActorCriticPolicy._predict at 0x7ca94524a4d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ca94524a560>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ca94524a5f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ca94524a680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ca9627eb340>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 3014656, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1691070567203544086, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQQAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYABAAAAAAAAM3CEb2kgFq5N5UMNEC4Ti2H6lA7QjejswAAgD8AAIA/HTiCPsjhPj+Vzho+mkcYv7llDz++WYk7AAAAAAAAAAAzfeq8mXS0P7ojNb8S6FO9HjWuPLpjUz0AAAAAAAAAALOvNr2P+ku6hYNxM0v7JTA5TjI7nlnHswAAgD8AAIA/M9NmPY+nArwVlc28f3iJO9E8aD37+IG8AACAPwAAgD9Stqe+k0Q1PySxujupgxu/NaT2vpH9sj0AAAAAAAAAAEZPR75igXs/Y/HPvvL5Q78c28++JrUCvgAAAAAAAAAAzW22PI4buT/A5N49tG0PvnC5aryONUA9AAAAAAAAAACaKU+84Dq5P5ZvMr5FUBk+350UvBeaPb0AAAAAAAAAAO0NN74sKro+Dq/EPUKkKr8sVFS+tdqwPQAAAAAAAAAAwPKBvfFEkT92A3K+sP1Tvw+J072SCmu+AAAAAAAAAADNKAE8Htm+P41hWz2+M7c86Uo5PK7bxLsAAAAAAAAAALPacz1YhdU+nAmROwBeRb8++rI9apObvAAAAAAAAAAAA1lnvgItcj9efMK+GmUyv8ut5r62iwK+AAAAAAAAAABNf5M+s39QP0awCr5Xsyu/nUIDP2kIh74AAAAAAAAAAIDCEb3AhqI+zb7jvHuORr9jDK+9luU+vQAAAAAAAAAA0MBrvjydij9p6Qe/sQQzvwNx4b50P4G+AAAAAAAAAABza60+KDt/P7xQyj2NYTy/FRg3P4pNG74AAAAAAAAAAM1aDD1ARZc+YKnevR0cQb+8kg48oYWDvQAAAAAAAAAAM9EGvWmZSbxK9J6+f+X1vZdQkj3YIrE+AAAAAAAAgD/tPRa+7WISP6d9tr2h00e/ddGfvvIz87wAAAAAAAAAADMhAT3D4Xq6psiAtvdon7EgsPC48AeUNQAAgD8AAIA/ADwavbGJsz0+ikg+nYXNvugz8Tx2cSM+AAAAAAAAAAAzi2g7H32VucmnDzXcVAowsnTSOP3FZ7QAAIA/AACAPzM3dbzsYda5TzeSPWzwI7PMgr67cptFswAAgD8AAIA/s3gBPU87QD7KExu9vsgVv39TszyGBp28AAAAAAAAAACzRvo9IdXXPgYm2L1kti2/mgMbPqYWJL4AAAAAAAAAANrBjz0SFOY8tkH5vaf2pr7E0w8++mm0vAAAAAAAAAAAAFAZvNf/ETrqNto97CiSNux8TbtgPqA1AACAPwAAgD8zT9q9/F/BPuEvLT2bMkW/ZWVcvsbyQz0AAAAAAAAAAJqfrDyp3nK8nlyVvpGLFDy4CNC97QD9PAAAgD8AAAAAAIyJO3tOkboecF61jBiksJPTuTmtH5E0AACAPwAAgD+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSyBLCIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.004885333333333408, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1840, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_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": 32, "n_steps": 1024, "gamma": 0.995, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 20, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "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": "3.10.12", "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-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 sha256:233c0e4238358c6e13a8b6433ceca1330622fb72a910ac2c9cf676b1384a8766
|
3 |
+
size 147324
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,20 +4,20 @@
|
|
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
|
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 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
@@ -26,16 +26,16 @@
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
-
":serialized:": "
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
@@ -45,13 +45,13 @@
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
@@ -76,15 +76,15 @@
|
|
76 |
"dtype": "int64",
|
77 |
"_np_random": null
|
78 |
},
|
79 |
-
"n_envs":
|
80 |
"n_steps": 1024,
|
81 |
-
"gamma": 0.
|
82 |
"gae_lambda": 0.98,
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
"batch_size": 64,
|
87 |
-
"n_epochs":
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":serialized:": "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"
|
|
|
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 0x7ca94524a050>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ca94524a0e0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ca94524a170>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ca94524a200>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7ca94524a290>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7ca94524a320>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7ca94524a3b0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ca94524a440>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7ca94524a4d0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ca94524a560>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ca94524a5f0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7ca94524a680>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7ca9627eb340>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1691070567203544086,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 1840,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
|
|
76 |
"dtype": "int64",
|
77 |
"_np_random": null
|
78 |
},
|
79 |
+
"n_envs": 32,
|
80 |
"n_steps": 1024,
|
81 |
+
"gamma": 0.995,
|
82 |
"gae_lambda": 0.98,
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
"batch_size": 64,
|
87 |
+
"n_epochs": 20,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":serialized:": "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"
|
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 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca2a35dc427f1959edefe0124dae90d1adf668de26f89ac901e5002b5b5f1c51
|
3 |
size 87929
|
ppo-LunarLander-v2/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:e6db52fcebccbb915b67937bc3c3d286560baefde9138b3c7d3bd975358fa008
|
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": 293.0250764650357, "std_reward": 24.656301450251977, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-03T15:18:22.492933"}
|