Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +1 -1
- ppo-LunarLander-v2/data +20 -20
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- ppo-LunarLander-v2/system_info.txt +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: 274.65 +/- 15.92
|
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 0x7ff4910d7dc0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff4910d7e50>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff4910d7ee0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff4910d7f70>", "_build": "<function ActorCriticPolicy._build at 0x7ff49105b040>", "forward": "<function ActorCriticPolicy.forward at 0x7ff49105b0d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff49105b160>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff49105b1f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff49105b280>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff49105b310>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff49105b3a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff49105b430>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7ff4910ceea0>"}, "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": 1673426543513760210, "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": 186, "n_steps": 2048, "gamma": 0.998, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 6, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0+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 0x7f8e3fc7ac10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8e3fc7aca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8e3fc7ad30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8e3fc7adc0>", "_build": "<function ActorCriticPolicy._build at 0x7f8e3fc7ae50>", "forward": "<function ActorCriticPolicy.forward at 0x7f8e3fc7aee0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8e3fc7af70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8e3fc7e040>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8e3fc7e0d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8e3fc7e160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8e3fc7e1f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8e3fc7e280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f8e3fc74b40>"}, "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": 1212416, "_total_timesteps": 1200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1673484036447477209, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_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": -0.010346666666666726, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 222, "n_steps": 2048, "gamma": 0.998, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 6, "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-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "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 147425
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7cd1c6930611a30657518fe8fc6480c0e0277e9b40888055fa7ee68f8ae2e941
|
3 |
size 147425
|
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_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
@@ -43,12 +43,12 @@
|
|
43 |
"_np_random": null
|
44 |
},
|
45 |
"n_envs": 16,
|
46 |
-
"num_timesteps":
|
47 |
-
"_total_timesteps":
|
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": {
|
@@ -57,7 +57,7 @@
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
-
":serialized:": "
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -67,16 +67,16 @@
|
|
67 |
"_episode_num": 0,
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
-
"_current_progress_remaining": -0.
|
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":
|
80 |
"n_steps": 2048,
|
81 |
"gamma": 0.998,
|
82 |
"gae_lambda": 0.98,
|
|
|
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 0x7f8e3fc7ac10>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8e3fc7aca0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8e3fc7ad30>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8e3fc7adc0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f8e3fc7ae50>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f8e3fc7aee0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8e3fc7af70>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8e3fc7e040>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f8e3fc7e0d0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8e3fc7e160>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8e3fc7e1f0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8e3fc7e280>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f8e3fc74b40>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
43 |
"_np_random": null
|
44 |
},
|
45 |
"n_envs": 16,
|
46 |
+
"num_timesteps": 1212416,
|
47 |
+
"_total_timesteps": 1200000,
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
+
"start_time": 1673484036447477209,
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "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"
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
67 |
"_episode_num": 0,
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.010346666666666726,
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "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"
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
77 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
},
|
79 |
+
"_n_updates": 222,
|
80 |
"n_steps": 2048,
|
81 |
"gamma": 0.998,
|
82 |
"gae_lambda": 0.98,
|
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 sha256:5e3dde539dc82ace3433e3de231fe3ee6c5f185ca0fb135cc13e0563055e3315
|
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 43393
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:def7820e844a39cf6ab5ebab7b0056ba4d600785a5a9a25f4ab4420e4a8b9418
|
3 |
size 43393
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
- OS: Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
- Python: 3.8.16
|
3 |
- Stable-Baselines3: 1.7.0
|
4 |
-
- PyTorch: 1.13.
|
5 |
- GPU Enabled: True
|
6 |
- Numpy: 1.21.6
|
7 |
- Gym: 0.21.0
|
|
|
1 |
- OS: Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
- Python: 3.8.16
|
3 |
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1+cu116
|
5 |
- GPU Enabled: True
|
6 |
- Numpy: 1.21.6
|
7 |
- Gym: 0.21.0
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 274.6538238831549, "std_reward": 15.923466389777218, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-12T01:08:23.000721"}
|