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/_stable_baselines3_version +1 -1
- ppo-LunarLander-v2/data +48 -44
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/system_info.txt +8 -6
- 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: 255.98 +/- 22.98
|
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 0x7f5532039040>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f55320390d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5532039160>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f55320391f0>", "_build": "<function ActorCriticPolicy._build at 0x7f5532039280>", "forward": "<function ActorCriticPolicy.forward at 0x7f5532039310>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f55320393a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5532039430>", "_predict": "<function ActorCriticPolicy._predict at 0x7f55320394c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5532039550>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f55320395e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5532039670>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f5532032b70>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1674984156789868684, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAAByzbzX+3a7g+T+vL9CET2F/rA8YvfxvQAAgD8AAIA/Myl7vNIUtjw+IDm904I9vsj4oLydGRY9AAAAAAAAAACzulc9hR5fP7Mp2LyZpr2+mI1MPYo35jwAAAAAAAAAAODehb52BY4/9ez5vf+MY77qxHq+damLPQAAAAAAAAAA5g1aPVh/Jj/T70y9tGqfvkVf7zwxdhS9AAAAAAAAAABaF5S99gxpuo27TrgeCVSzZ2VGO+iMcjcAAIA/AACAP2ZmAbspBHO6AJPStV8sU7EnnAc7Fe34NAAAgD8AAIA/zSR0vHY3KLxer7u8UKYiPSphiz3/JQS+AACAPwAAgD9tnUc+F7EyP53vkry+A5W+BrLsPZK/l70AAAAAAAAAALMGFb4ctAS8C2/ovGlsQbu3wWg9gfEhPAAAgD8AAIA/mqfZPWYT3j4OJze9tHSGvg8icjz6Plm9AAAAAAAAAAAmqLy9ZmQJP380hz4bFY6+NCaGPahhjD0AAAAAAAAAALPs/T3XLGM+fiYAvoarZr7QQ7U8xhbgPAAAAAAAAAAAZmqkvDa7Xj8vUMc95yeevvbas7uLcjO9AAAAAAAAAAAa41w9oXOFPYvoUL001y2+YBD4u1ZZpTsAAAAAAAAAAPPZwz0SuyI+ylDQvR3uN76Sa9u7TtnIPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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": 248, "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-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
|
|
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 0x7d383df045e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d383df04670>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d383df04700>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d383df04790>", "_build": "<function ActorCriticPolicy._build at 0x7d383df04820>", "forward": "<function ActorCriticPolicy.forward at 0x7d383df048b0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d383df04940>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d383df049d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7d383df04a60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d383df04af0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d383df04b80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d383df04c10>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d383e092c40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1693170607001263967, "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": -0.015808000000000044, "_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": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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": 4, "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": "1.23.5", "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 sha256:74000c52822583f0d5d7ebff9d7f2b9da685fa1e86e13eb492d5e599c7a1ce75
|
3 |
+
size 146746
|
ppo-LunarLander-v2/_stable_baselines3_version
CHANGED
@@ -1 +1 @@
|
|
1 |
-
|
|
|
1 |
+
2.0.0a5
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,60 +4,34 @@
|
|
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_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"observation_space": {
|
25 |
-
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
-
":serialized:": "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",
|
27 |
-
"dtype": "float32",
|
28 |
-
"_shape": [
|
29 |
-
8
|
30 |
-
],
|
31 |
-
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
32 |
-
"high": "[inf inf inf inf inf inf inf inf]",
|
33 |
-
"bounded_below": "[False False False False False False False False]",
|
34 |
-
"bounded_above": "[False False False False False False False False]",
|
35 |
-
"_np_random": null
|
36 |
-
},
|
37 |
-
"action_space": {
|
38 |
-
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
39 |
-
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
40 |
-
"n": 4,
|
41 |
-
"_shape": [],
|
42 |
-
"dtype": "int64",
|
43 |
-
"_np_random": null
|
44 |
-
},
|
45 |
-
"n_envs": 16,
|
46 |
"num_timesteps": 1015808,
|
47 |
"_total_timesteps": 1000000,
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
-
"start_time":
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
-
"lr_schedule": {
|
55 |
-
":type:": "<class 'function'>",
|
56 |
-
":serialized:": "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"
|
57 |
-
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
-
":serialized:": "
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -68,15 +42,41 @@
|
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
"_current_progress_remaining": -0.015808000000000044,
|
|
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
-
":serialized:": "
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
77 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
},
|
79 |
"_n_updates": 248,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
@@ -87,9 +87,13 @@
|
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
-
":serialized:": "
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
-
"target_kl": null
|
|
|
|
|
|
|
|
|
95 |
}
|
|
|
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 0x7d383df045e0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d383df04670>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d383df04700>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d383df04790>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7d383df04820>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7d383df048b0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7d383df04940>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d383df049d0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7d383df04a60>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d383df04af0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d383df04b80>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7d383df04c10>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7d383e092c40>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
"num_timesteps": 1015808,
|
25 |
"_total_timesteps": 1000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1693170607001263967,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
|
|
|
|
|
|
|
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAJpDYr17PoO6UuVOOeAvSzQIhko5mLJpuAAAAAAAAIA/ADBsPpXlfj6SVt+9otCMvnPGAT0hf528AAAAAAAAAADmRko9jw4UukzLv7t/rYw4jFGxupo8XjoAAIA/AACAP2YA67z2SHK6YuzjOoSRYbUBUge7bUQCugAAgD8AAIA/5jpOvVybfLoOAtW6GSE1thCuXDreU/U5AACAPwAAgD9mCkg94TyKus+jsDuqK9Y3njzSOvZBhjYAAIA/AACAP209Gb7556Q+FrnePUO6j75EYkq8JozOvAAAAAAAAAAA05UbPgoofLtu5w24LtIKNZRNpbzVlCQ3AACAPwAAgD+ajk09ZVBxPgbmx7yWda++HGtDPL4757wAAAAAAAAAAABrTj1IV5a60SbHuUBM6zWqdIA5ru/lOAAAgD8AAIA/gBsZPVue1rwOrww8J/XgORRuMr5uVBK+AACAPwAAgD9mKMI8SHGLuq3vH7lEPA20YObsun/6OTgAAIA/AACAPzN/Uj5oPao+gZu0vQcBmL6+xrk78XjGPAAAAAAAAAAA5gthPeHAmbodg2e5pL9wtBt+grqHOoU4AACAPwAAgD+mZLo9pJBNuZ1BezmK9rg00hA1Oyvsk7gAAIA/AACAPwDzRz3DbWS6WVWdu62WmTiAYAm7OJJOOQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
"_current_progress_remaining": -0.015808000000000044,
|
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": 248,
|
55 |
+
"observation_space": {
|
56 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
+
"dtype": "float32",
|
59 |
+
"bounded_below": "[ True True True True True True True True]",
|
60 |
+
"bounded_above": "[ True True True True True True True True]",
|
61 |
+
"_shape": [
|
62 |
+
8
|
63 |
+
],
|
64 |
+
"low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
65 |
+
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
66 |
+
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
67 |
+
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
68 |
+
"_np_random": null
|
69 |
+
},
|
70 |
+
"action_space": {
|
71 |
+
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"n": "4",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
77 |
+
"_np_random": null
|
78 |
+
},
|
79 |
+
"n_envs": 16,
|
80 |
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
|
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "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"
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
+
"target_kl": null,
|
95 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
+
}
|
99 |
}
|
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 sha256:2cd4305c273cd39daa57499be81e83be6c1b21bfc617ce58955b3a9acbbb467c
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f234737390a8471f31b0cfcc612b0e86cda70c487b8388c0131a0f25a7b6d90
|
3 |
+
size 43329
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,7 +1,9 @@
|
|
1 |
-
- OS: Linux-5.
|
2 |
-
- Python: 3.
|
3 |
-
- Stable-Baselines3:
|
4 |
-
- PyTorch:
|
5 |
- GPU Enabled: True
|
6 |
-
- Numpy: 1.
|
7 |
-
-
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.0.1+cu118
|
5 |
- GPU Enabled: True
|
6 |
+
- Numpy: 1.23.5
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 255.9792766574808, "std_reward": 22.979899068660973, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-27T21:34:17.196115"}
|