Harri/PPO-LunadLander-v2
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +16 -16
- 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: 263.28 +/- 18.31
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7fbf4690a790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbf4690a820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbf4690a8b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbf4690a940>", "_build": "<function ActorCriticPolicy._build at 0x7fbf4690a9d0>", "forward": "<function ActorCriticPolicy.forward at 0x7fbf4690aa60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbf4690aaf0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fbf4690ab80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbf4690ac10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbf4690aca0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbf4690ad30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fbf4690b0f0>"}, "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": 1670955711316622663, "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": 320, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7fea9b6f89d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fea9b6f8a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fea9b6f8af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fea9b6f8b80>", "_build": "<function ActorCriticPolicy._build at 0x7fea9b6f8c10>", "forward": "<function ActorCriticPolicy.forward at 0x7fea9b6f8ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fea9b6f8d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7fea9b6f8dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fea9b6f8e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fea9b6f8ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fea9b6f8f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fea9b6fb0c0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 1671124628424438295, "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": 310, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0e306171515f3302f17a8fc6ac06b47ff7112dcee5671c9497395252580baae
|
3 |
+
size 147109
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,19 +4,19 @@
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
-
"_abc_impl": "<_abc_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
@@ -47,7 +47,7 @@
|
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
-
"start_time":
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
@@ -56,7 +56,7 @@
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -69,13 +69,13 @@
|
|
69 |
"_current_progress_remaining": -0.015808000000000044,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
"n_steps": 2048,
|
80 |
"gamma": 0.99,
|
81 |
"gae_lambda": 0.95,
|
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7fea9b6f89d0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fea9b6f8a60>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fea9b6f8af0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fea9b6f8b80>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fea9b6f8c10>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fea9b6f8ca0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fea9b6f8d30>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fea9b6f8dc0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fea9b6f8e50>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fea9b6f8ee0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fea9b6f8f70>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fea9b6fb0c0>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1671124628424438295,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
69 |
"_current_progress_remaining": -0.015808000000000044,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "gAWVMBAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIM4ekFko9bkCUhpRSlIwBbJRLx4wBdJRHQJbStRZU1ht1fZQoaAZoCWgPQwjIQQkzLRBxQJSGlFKUaBVL02gWR0CW0rg7YChfdX2UKGgGaAloD0MI+wW7YduicUCUhpRSlGgVS89oFkdAltOVinYQKHV9lChoBmgJaA9DCBmRKLTsAnJAlIaUUpRoFUvvaBZHQJbT2A7Pppx1fZQoaAZoCWgPQwgRc0nVtq9xQJSGlFKUaBVLvWgWR0CW1CShrWRSdX2UKGgGaAloD0MIwyy0c1rKcUCUhpRSlGgVS9xoFkdAltUexW1c+3V9lChoBmgJaA9DCMnJxK0CwXNAlIaUUpRoFU06AWgWR0CW1TwfQrtmdX2UKGgGaAloD0MI5IOezaoeb0CUhpRSlGgVS8FoFkdAltVWkadc0XV9lChoBmgJaA9DCBK9jGJ5VnFAlIaUUpRoFUvOaBZHQJbVzr6ciGF1fZQoaAZoCWgPQwjdeeI528RtQJSGlFKUaBVLw2gWR0CW1xLc9GI9dX2UKGgGaAloD0MIwocSLfkdb0CUhpRSlGgVS8poFkdAltckZNwiq3V9lChoBmgJaA9DCKm8HeE0knBAlIaUUpRoFUvkaBZHQJbXgY64lQd1fZQoaAZoCWgPQwgxCoLHN2hwQJSGlFKUaBVL02gWR0CW1/2cJ+lTdX2UKGgGaAloD0MIBTV8CysscECUhpRSlGgVS85oFkdAltjtKdxyXHV9lChoBmgJaA9DCMSVs3fG0mFAlIaUUpRoFU3oA2gWR0CW2SIkZ75VdX2UKGgGaAloD0MIHofB/BWfcUCUhpRSlGgVS8BoFkdAltk6FmFrVXV9lChoBmgJaA9DCKq7sguGPXBAlIaUUpRoFUvPaBZHQJbZRYigTRJ1fZQoaAZoCWgPQwhanDHMScZwQJSGlFKUaBVLs2gWR0CW2f1IAfdRdX2UKGgGaAloD0MIKGN8mD0fcUCUhpRSlGgVTXQBaBZHQJbbKfQKKHh1fZQoaAZoCWgPQwiF0EGXMLhxQJSGlFKUaBVNVQFoFkdAltvUWAPNFHV9lChoBmgJaA9DCM/zp43qVXJAlIaUUpRoFUvUaBZHQJbb/Gza9K51fZQoaAZoCWgPQwgAGxAhLu9wQJSGlFKUaBVL/WgWR0CW3JufVZs9dX2UKGgGaAloD0MIRrHc0upxcECUhpRSlGgVS7loFkdAltz30kGA1HV9lChoBmgJaA9DCNOgaB5ApW1AlIaUUpRoFUvMaBZHQJbdFceKba11fZQoaAZoCWgPQwghrTHoRHlzQJSGlFKUaBVLuWgWR0CW3n0pVjqfdX2UKGgGaAloD0MIRRK9jGJ9cECUhpRSlGgVS9toFkdAlt6HCwbEP3V9lChoBmgJaA9DCBJqhlTRPG5AlIaUUpRoFUvRaBZHQJbfez1K5Cp1fZQoaAZoCWgPQwgB9zx/GhNxQJSGlFKUaBVLzmgWR0CW33+4LCvYdX2UKGgGaAloD0MIbXTOT7FicUCUhpRSlGgVTRMBaBZHQJbhyYmb9ZR1fZQoaAZoCWgPQwh1kNeDSRhwQJSGlFKUaBVLu2gWR0CW4pXDFZPmdX2UKGgGaAloD0MIpGyRtJtJc0CUhpRSlGgVTQ8BaBZHQJbio0xdpqR1fZQoaAZoCWgPQwhOQukLoR9vQJSGlFKUaBVL2GgWR0CW4unWrfcfdX2UKGgGaAloD0MI5L7VOvF8bkCUhpRSlGgVS/RoFkdAluMNpM6BAnV9lChoBmgJaA9DCGUYd4PopXFAlIaUUpRoFUu/aBZHQJbjSI55qud1fZQoaAZoCWgPQwglCFdA4TJyQJSGlFKUaBVL5WgWR0CW5FaMrEtNdX2UKGgGaAloD0MIou2YuquccECUhpRSlGgVTRABaBZHQJbkgornTy91fZQoaAZoCWgPQwhV+glnt+5EQJSGlFKUaBVLumgWR0CW5Iq6vq1PdX2UKGgGaAloD0MI02weh4GFcUCUhpRSlGgVS89oFkdAluUro4dZJXV9lChoBmgJaA9DCDXR56NMDnFAlIaUUpRoFUu/aBZHQJblmSA6Mit1fZQoaAZoCWgPQwgCKhxBKthvQJSGlFKUaBVL32gWR0CW5pSRbKRudX2UKGgGaAloD0MInDV4X5UscECUhpRSlGgVS79oFkdAlufH4Glhw3V9lChoBmgJaA9DCJ5+UBcppEJAlIaUUpRoFUupaBZHQJboFSpBHCp1fZQoaAZoCWgPQwi/0Y4bfkpwQJSGlFKUaBVLx2gWR0CW6MYCyQgcdX2UKGgGaAloD0MICd0lcdajcECUhpRSlGgVS75oFkdAlupEYTCcgHV9lChoBmgJaA9DCGCTNeohnG9AlIaUUpRoFUvLaBZHQJbq+57PY4B1fZQoaAZoCWgPQwiespquJ5thQJSGlFKUaBVN6ANoFkdAlus2PYFqz3V9lChoBmgJaA9DCB8wD5lyJ3FAlIaUUpRoFUv8aBZHQJbrUmWt2cJ1fZQoaAZoCWgPQwhhTzv8tbJwQJSGlFKUaBVLx2gWR0CW66U6PsAvdX2UKGgGaAloD0MIPZ6WH/gRcUCUhpRSlGgVTSEBaBZHQJbr5ivxH5J1fZQoaAZoCWgPQwicTx2rlDZyQJSGlFKUaBVL22gWR0CW7KeqJdjYdX2UKGgGaAloD0MITG2pgzxZcUCUhpRSlGgVS8ZoFkdAluz/JzT4L3V9lChoBmgJaA9DCBEdAkfCZnBAlIaUUpRoFUvDaBZHQJbuHYVZcLV1fZQoaAZoCWgPQwgS9YJP84ZhQJSGlFKUaBVN6ANoFkdAlu6AZ0jkdXV9lChoBmgJaA9DCKvsuyK4bHBAlIaUUpRoFU08AWgWR0CW7pG3F1jidX2UKGgGaAloD0MIU0Kwqt6obkCUhpRSlGgVS9NoFkdAlu7kjs2NvXV9lChoBmgJaA9DCMfUXdkFwHBAlIaUUpRoFUveaBZHQJbvvr6ciGF1fZQoaAZoCWgPQwjIJCNn4eRvQJSGlFKUaBVLvGgWR0CW8KIRRMvidX2UKGgGaAloD0MIgXueP61qcUCUhpRSlGgVS+BoFkdAlvEmtU4rBnV9lChoBmgJaA9DCBGMg0uHynJAlIaUUpRoFUvPaBZHQJbxZNDc/MZ1fZQoaAZoCWgPQwgYey++6PBtQJSGlFKUaBVL0mgWR0CW8ZOFQEZBdX2UKGgGaAloD0MIhNiZQudccUCUhpRSlGgVS8ZoFkdAlvJ7XYlIE3V9lChoBmgJaA9DCP7XuWmzCW9AlIaUUpRoFUvAaBZHQJbyo1baAWl1fZQoaAZoCWgPQwiHhsWoK8pxQJSGlFKUaBVL9mgWR0CW8ySF49owdX2UKGgGaAloD0MILNhGPFlgYECUhpRSlGgVTegDaBZHQJbzuqIacZt1fZQoaAZoCWgPQwig4c0aPKltQJSGlFKUaBVL5GgWR0CW9QQ3xWkrdX2UKGgGaAloD0MIG9e/67MNb0CUhpRSlGgVS+JoFkdAlvVZlvqC6HV9lChoBmgJaA9DCIi+u5WlYG5AlIaUUpRoFUvJaBZHQJb1j3bmEGt1fZQoaAZoCWgPQwhS7dPxmLxwQJSGlFKUaBVNBAFoFkdAlvWXGn4wiHV9lChoBmgJaA9DCBTQRNjwemNAlIaUUpRoFU3oA2gWR0CW9bHRTjvNdX2UKGgGaAloD0MIrvVFQtsTckCUhpRSlGgVS9NoFkdAlvaFlPJq7HV9lChoBmgJaA9DCNCX3v7cOG9AlIaUUpRoFUvEaBZHQJb2k+TvAoJ1fZQoaAZoCWgPQwidR8X/HelwQJSGlFKUaBVL6mgWR0CW99QnhKlIdX2UKGgGaAloD0MIAvBPqRJrcUCUhpRSlGgVS+loFkdAlvf5WV/tpnV9lChoBmgJaA9DCC5x5IHIrXFAlIaUUpRoFUvMaBZHQJb4LicXm/51fZQoaAZoCWgPQwjoEg69RVdxQJSGlFKUaBVL32gWR0CW+a6guh9LdX2UKGgGaAloD0MIYp0q33OfckCUhpRSlGgVS7xoFkdAlvqmX1J173V9lChoBmgJaA9DCAsMWd1qZmtAlIaUUpRoFUvIaBZHQJb6wgV45cV1fZQoaAZoCWgPQwitFW2Oc8hxQJSGlFKUaBVL12gWR0CW+4OsT37DdX2UKGgGaAloD0MIRfMAFnlzcUCUhpRSlGgVS7ZoFkdAlvvIrjHXE3V9lChoBmgJaA9DCO4nY3wY6nFAlIaUUpRoFUvzaBZHQJb7yLQ5WBB1fZQoaAZoCWgPQwgO8+UFWGtxQJSGlFKUaBVL7mgWR0CW/FhMrVe8dX2UKGgGaAloD0MIvXDnwsjGcUCUhpRSlGgVS+ZoFkdAlv0nbZezEHV9lChoBmgJaA9DCGa7Qh+snm1AlIaUUpRoFUveaBZHQJb+cPwuuih1fZQoaAZoCWgPQwgUCaaaWYZxQJSGlFKUaBVL3WgWR0CW/pTJhfBvdX2UKGgGaAloD0MIVJCfjRw9cUCUhpRSlGgVS9loFkdAlv66QNkOJHV9lChoBmgJaA9DCIrmASzyfWRAlIaUUpRoFU3oA2gWR0CXAU6ij+JhdX2UKGgGaAloD0MIR68GKI3DcECUhpRSlGgVS69oFkdAlwGZ7PY4AHV9lChoBmgJaA9DCEfH1ciubm9AlIaUUpRoFU0AAWgWR0CXAgvTPSlWdX2UKGgGaAloD0MIx4MtdntLbUCUhpRSlGgVS89oFkdAlwKambb1y3V9lChoBmgJaA9DCIuH9xyY2XBAlIaUUpRoFUvfaBZHQJcC0c94eLh1fZQoaAZoCWgPQwjAAwMIn9xuQJSGlFKUaBVLz2gWR0CXAzMRHww1dX2UKGgGaAloD0MIXmkZqbeHcUCUhpRSlGgVS+JoFkdAlwSStaIN3HV9lChoBmgJaA9DCB7BjZTtS3FAlIaUUpRoFU0+AWgWR0CXBO3CKrJbdX2UKGgGaAloD0MImS7E6g+CcECUhpRSlGgVS91oFkdAlwWv+n62v3V9lChoBmgJaA9DCADmWrTAlXBAlIaUUpRoFUvHaBZHQJcHzx3FDOV1fZQoaAZoCWgPQwgN+tLbH89wQJSGlFKUaBVLuWgWR0CXCMV9F4LUdX2UKGgGaAloD0MIZjIczyflcECUhpRSlGgVS81oFkdAlwjXo5ggHXV9lChoBmgJaA9DCJIIjWDjbXFAlIaUUpRoFU02AWgWR0CXCRAeJYT1dX2UKGgGaAloD0MIp1t2iH+lbUCUhpRSlGgVS8toFkdAlwmnV5KODXV9lChoBmgJaA9DCB7f3jXoD2JAlIaUUpRoFU3oA2gWR0CXClsOG0u2dWUu"
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 310,
|
79 |
"n_steps": 2048,
|
80 |
"gamma": 0.99,
|
81 |
"gae_lambda": 0.95,
|
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:f305dd48a5c44334aab328517b88b2b3fb23c8406d45a37a1d78683545293294
|
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 43201
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cf4ec5b9a47990bf319cbe34b1e466eb13fedd3f6b605337e0973e3c63b572c
|
3 |
size 43201
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 263.28247379922857, "std_reward": 18.305920265336624, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-15T17:56:18.550064"}
|