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 +20 -20
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +2 -2
- 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: 221.75 +/- 81.24
|
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 0x7fabbbd97c10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fabbbd97ca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fabbbd97d30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fabbbd97dc0>", "_build": "<function ActorCriticPolicy._build at 0x7fabbbd97e50>", "forward": "<function ActorCriticPolicy.forward at 0x7fabbbd97ee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fabbbd97f70>", "_predict": "<function ActorCriticPolicy._predict at 0x7fabbbd9d040>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fabbbd9d0d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fabbbd9d160>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fabbbd9d1f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fabbbd944b0>"}, "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": 1672754791871652972, "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": -0.010346666666666726, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 296, "n_steps": 1024, "gamma": 0.97, "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-5.10.133+-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 0x7f37d86bff70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f37d86c6040>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f37d86c60d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f37d86c6160>", "_build": "<function ActorCriticPolicy._build at 0x7f37d86c61f0>", "forward": "<function ActorCriticPolicy.forward at 0x7f37d86c6280>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f37d86c6310>", "_predict": "<function ActorCriticPolicy._predict at 0x7f37d86c63a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f37d86c6430>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f37d86c64c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f37d86c6550>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f37d86c2180>"}, "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": 1672773330924682767, "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": 248, "n_steps": 1024, "gamma": 0.9999, "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:": "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"}}
|
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 sha256:31e462d01a57438ad370409cc7e087c6ff040f9d0df2d4f7ce90cfc4fb2523c4
|
3 |
+
size 147211
|
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": {},
|
@@ -42,12 +42,12 @@
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
-
"num_timesteps":
|
46 |
-
"_total_timesteps":
|
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'>",
|
@@ -66,18 +66,18 @@
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining": -0.
|
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": 1024,
|
80 |
-
"gamma": 0.
|
81 |
"gae_lambda": 0.98,
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
|
|
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 0x7f37d86bff70>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f37d86c6040>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f37d86c60d0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f37d86c6160>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f37d86c61f0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f37d86c6280>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f37d86c6310>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f37d86c63a0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f37d86c6430>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f37d86c64c0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f37d86c6550>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f37d86c2180>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1672773330924682767,
|
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'>",
|
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.015808000000000044,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "gAWVehAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIbqRskXTXcUCUhpRSlIwBbJRNMQGMAXSUR0C2kx12A5JcdX2UKGgGaAloD0MIRIZVvJEhcECUhpRSlGgVTVABaBZHQLaTz/ACW/t1fZQoaAZoCWgPQwgaa39nu6pyQJSGlFKUaBVNPgFoFkdAtpPxrhzeXXV9lChoBmgJaA9DCFlrKLXXG3FAlIaUUpRoFU0tAWgWR0C2mTTx9XtCdX2UKGgGaAloD0MI7G0zFWLAcECUhpRSlGgVTWEBaBZHQLaZo8V58jR1fZQoaAZoCWgPQwjM0k7N5cpxQJSGlFKUaBVNoQFoFkdAtpm+6GxlhHV9lChoBmgJaA9DCK4oJQSrTj1AlIaUUpRoFUvxaBZHQLaZ98hcJMR1fZQoaAZoCWgPQwgNjSeC+JByQJSGlFKUaBVNFQFoFkdAtpoH4gzP8nV9lChoBmgJaA9DCGnIeJTK4HJAlIaUUpRoFU0HAWgWR0C2mhgydnTRdX2UKGgGaAloD0MIm6285H8qckCUhpRSlGgVTToBaBZHQLaaGmJFb3Z1fZQoaAZoCWgPQwj4+e/B6/ZwQJSGlFKUaBVNHAFoFkdAtppDh99c8nV9lChoBmgJaA9DCAagUbo0I3BAlIaUUpRoFU1UAWgWR0C2mki+lCTmdX2UKGgGaAloD0MIXDl7Z7RKbUCUhpRSlGgVTX4BaBZHQLaad3xnWat1fZQoaAZoCWgPQwjFq6xtit9xQJSGlFKUaBVNvQFoFkdAtpqWmBOHnHV9lChoBmgJaA9DCF7zqs4qD3FAlIaUUpRoFU14AWgWR0C2msOJcgQpdX2UKGgGaAloD0MIVijS/ZwfcECUhpRSlGgVTX8BaBZHQLaa34sEq2B1fZQoaAZoCWgPQwjDmsqisLhvQJSGlFKUaBVNjQFoFkdAtprquQp4KXV9lChoBmgJaA9DCPxQacSM7HFAlIaUUpRoFU0jAWgWR0C2myo7muDBdX2UKGgGaAloD0MInrKarucvcUCUhpRSlGgVTRoBaBZHQLabNd8zAN51fZQoaAZoCWgPQwjFrBdDOZ9vQJSGlFKUaBVNIgFoFkdAtpu4NEw353V9lChoBmgJaA9DCB5rRga54UhAlIaUUpRoFUvvaBZHQLab5lPrOZ91fZQoaAZoCWgPQwgKvJNPD01rQJSGlFKUaBVNGwFoFkdAtpwDyrgfl3V9lChoBmgJaA9DCDKOkeyR/m1AlIaUUpRoFU0mAWgWR0C2nJB1Tzd2dX2UKGgGaAloD0MIMVwdADE/cUCUhpRSlGgVTUsBaBZHQLacmSUC7sh1fZQoaAZoCWgPQwi9NbBVAvpvQJSGlFKUaBVNQgFoFkdAtpzH/cWTHXV9lChoBmgJaA9DCF/SGK1ju3JAlIaUUpRoFU1TAWgWR0C2nQTF+/g0dX2UKGgGaAloD0MI6lvmdFkMcECUhpRSlGgVTSMBaBZHQLadEYwqRU51fZQoaAZoCWgPQwgcCp+tAwFvQJSGlFKUaBVNIAFoFkdAtp16FDfFaXV9lChoBmgJaA9DCMmwijeyR3FAlIaUUpRoFU1bAWgWR0C2nXo0Q9RrdX2UKGgGaAloD0MIDoelgR9lRUCUhpRSlGgVTQoBaBZHQLadr+VTrE91fZQoaAZoCWgPQwhtyD8zCNlvQJSGlFKUaBVNXwFoFkdAtp3Z07r9l3V9lChoBmgJaA9DCAtD5PT1fXFAlIaUUpRoFU1kAWgWR0C2ngXYHxBmdX2UKGgGaAloD0MI+TB72fZpa0CUhpRSlGgVTdUBaBZHQLaeXtr9ETh1fZQoaAZoCWgPQwgiUP2DSA9yQJSGlFKUaBVNNQFoFkdAtp7Ohf0Eo3V9lChoBmgJaA9DCNHmOLcJyUxAlIaUUpRoFUvvaBZHQLae0NLDhtN1fZQoaAZoCWgPQwj1vYbguPJyQJSGlFKUaBVNSwFoFkdAtp7TNliBoXV9lChoBmgJaA9DCEA08+RaJHJAlIaUUpRoFU1KAWgWR0C2nxyd8RcvdX2UKGgGaAloD0MISkVj7W8rcUCUhpRSlGgVTc4BaBZHQLafYWluWKN1fZQoaAZoCWgPQwhTXFX2HadwQJSGlFKUaBVNMAFoFkdAtp+XgzguRXV9lChoBmgJaA9DCDiie9a1s25AlIaUUpRoFU0dAWgWR0C2n6IHcDbKdX2UKGgGaAloD0MIdJtwrwxbcUCUhpRSlGgVTRkBaBZHQLafpQ/oq1B1fZQoaAZoCWgPQwhhMlUwKu9sQJSGlFKUaBVNbgJoFkdAtp/EiiZfD3V9lChoBmgJaA9DCN6swfsq421AlIaUUpRoFU1sAWgWR0C2n+xVlwtKdX2UKGgGaAloD0MIBrr2BXT9b0CUhpRSlGgVTRMBaBZHQLaf8Qzk6tF1fZQoaAZoCWgPQwihEtcx7p9yQJSGlFKUaBVL9mgWR0C2oAgDmr80dX2UKGgGaAloD0MIOEnzx3RjcUCUhpRSlGgVTR4BaBZHQLagMwiaAnV1fZQoaAZoCWgPQwgMWkjAaIVuQJSGlFKUaBVNRwFoFkdAtqBUDifg8HV9lChoBmgJaA9DCCmTGtoA1m5AlIaUUpRoFU0/AWgWR0C2oMA2ycCpdX2UKGgGaAloD0MIQwHbwUhPckCUhpRSlGgVS/JoFkdAtqDXBAOav3V9lChoBmgJaA9DCJXurrMhY3BAlIaUUpRoFU09AWgWR0C2oQ7212JSdX2UKGgGaAloD0MIP6n26ThHcUCUhpRSlGgVTQwBaBZHQLahEMsYl6Z1fZQoaAZoCWgPQwgLuOf5U1txQJSGlFKUaBVNJgFoFkdAtqFCHuZ1FHV9lChoBmgJaA9DCBiWP9+WqW5AlIaUUpRoFU1CAWgWR0C2odOQQtjDdX2UKGgGaAloD0MIgXaHFEMlcUCUhpRSlGgVTVEBaBZHQLanCUOuq3p1fZQoaAZoCWgPQwiIug9A6mtxQJSGlFKUaBVNRwFoFkdAtqcsUqQRw3V9lChoBmgJaA9DCK+V0F3SmnFAlIaUUpRoFU1dAWgWR0C2p3ef/WDpdX2UKGgGaAloD0MIIZBLHHlrb0CUhpRSlGgVTTYBaBZHQLanlXV9Wp91fZQoaAZoCWgPQwhd4sgDkYZuQJSGlFKUaBVNWAFoFkdAtqfPfgrH2nV9lChoBmgJaA9DCMi1oWJcMXBAlIaUUpRoFU0oAWgWR0C2p+B5gPVedX2UKGgGaAloD0MIJzEIrFwGcUCUhpRSlGgVTYkBaBZHQLan918b70p1fZQoaAZoCWgPQwhSYAFMGdVyQJSGlFKUaBVNSwFoFkdAtqgKQhfShXV9lChoBmgJaA9DCDhm2ZNAKnBAlIaUUpRoFU2BAWgWR0C2qDmA9V3mdX2UKGgGaAloD0MIQBaiQ+ApckCUhpRSlGgVTQkBaBZHQLaoc6iCaql1fZQoaAZoCWgPQwhQNuUK719uQJSGlFKUaBVNWQFoFkdAtqjSs1baAXV9lChoBmgJaA9DCBZLkXwlsnFAlIaUUpRoFU0zAWgWR0C2qRBFRYRvdX2UKGgGaAloD0MIRS44g7/EcUCUhpRSlGgVTfYBaBZHQLapGBRAKOV1fZQoaAZoCWgPQwimuoCXGf9rQJSGlFKUaBVNYwFoFkdAtqlBklNUO3V9lChoBmgJaA9DCPuytFMzkXBAlIaUUpRoFU2LAWgWR0C2qVuCTUy6dX2UKGgGaAloD0MIeM+B5chFckCUhpRSlGgVTQwBaBZHQLapl8+iaiN1fZQoaAZoCWgPQwikU1c+C0ZzQJSGlFKUaBVNUgFoFkdAtqnW9qUNa3V9lChoBmgJaA9DCGOYE7RJyG9AlIaUUpRoFU0xAWgWR0C2qm2Af+0gdX2UKGgGaAloD0MI09o0theQcECUhpRSlGgVTV4BaBZHQLaqh8DB/I91fZQoaAZoCWgPQwit+IbCZ+5tQJSGlFKUaBVNKAFoFkdAtqqNPLxI8XV9lChoBmgJaA9DCBxF1hpK9G1AlIaUUpRoFU0zAWgWR0C2qtNOVPepdX2UKGgGaAloD0MIrg0V4/z+a0CUhpRSlGgVTUQBaBZHQLarTco6S1V1fZQoaAZoCWgPQwgbnIh+7VBzQJSGlFKUaBVNQwFoFkdAtquVfShJy3V9lChoBmgJaA9DCJJ55A8Gr25AlIaUUpRoFU1FAWgWR0C2rBgjD8+BdX2UKGgGaAloD0MIwono19bpcECUhpRSlGgVTbEBaBZHQLasJ55qubJ1fZQoaAZoCWgPQwjZ0M3+AMVyQJSGlFKUaBVNMQFoFkdAtqwrQE6kqXV9lChoBmgJaA9DCEWBPpFnGnJAlIaUUpRoFU3PAWgWR0C2rKgDV6NVdX2UKGgGaAloD0MITx4Was2UbECUhpRSlGgVTWUBaBZHQLaswsU7CBR1fZQoaAZoCWgPQwhfuHNhJClsQJSGlFKUaBVNLwFoFkdAtqzXxQSBb3V9lChoBmgJaA9DCIf58gJsYXBAlIaUUpRoFU1oAWgWR0C2rRmitaIOdX2UKGgGaAloD0MIWaX0TG9hcUCUhpRSlGgVTTMBaBZHQLatIvAGjbl1fZQoaAZoCWgPQwiInpRJDRxxQJSGlFKUaBVNqgFoFkdAtq2ZurIYFnV9lChoBmgJaA9DCCb/k7/7QXBAlIaUUpRoFU1DAWgWR0C2rdkNvwVkdX2UKGgGaAloD0MIyZHOwEhIckCUhpRSlGgVTU0BaBZHQLauCYgq3E11fZQoaAZoCWgPQwhuowG8xS1wQJSGlFKUaBVNVAFoFkdAtq5fHKfWc3V9lChoBmgJaA9DCMPTK2XZR3JAlIaUUpRoFU0PAWgWR0C2rl7vw3HadX2UKGgGaAloD0MI7YLBNbeBcUCUhpRSlGgVTSgBaBZHQLauYgLJCBx1fZQoaAZoCWgPQwgp7KLogTtuQJSGlFKUaBVNdQFoFkdAtq5qYXwb2nV9lChoBmgJaA9DCDv8NVljEHFAlIaUUpRoFUv6aBZHQLaul1cMVlB1fZQoaAZoCWgPQwgEOShhplxuQJSGlFKUaBVNKgFoFkdAtq71OafBe3V9lChoBmgJaA9DCMAGRIirv3FAlIaUUpRoFU0yAWgWR0C2rxWd/axpdX2UKGgGaAloD0MIUvF/RxRqc0CUhpRSlGgVS/BoFkdAtq9UXVLBbnV9lChoBmgJaA9DCBYUBmVaM3BAlIaUUpRoFU0mAWgWR0C2r2FMdtEYdX2UKGgGaAloD0MIAmISLuRjbkCUhpRSlGgVTSwBaBZHQLavgRWcSXd1fZQoaAZoCWgPQwjChTyCGyxwQJSGlFKUaBVNBQFoFkdAtq/uTLW7OHV9lChoBmgJaA9DCI/66xWWVnFAlIaUUpRoFU17AWgWR0C2sEuUyHmBdX2UKGgGaAloD0MIM/0S8ZZXcECUhpRSlGgVTWEBaBZHQLawTez2OAB1ZS4="
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 248,
|
79 |
"n_steps": 1024,
|
80 |
+
"gamma": 0.9999,
|
81 |
"gae_lambda": 0.98,
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
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:d087f4f5633b7dbcbb8dae79328e6f7d1cf5d841d19644e0798fe78524ff454a
|
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:d2ba50d7b86c747c0e8d267e7c8d08bab648e6136fc4480c3a1c2d25a6928d51
|
3 |
size 43201
|
replay.mp4
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 sha256:6a0b42c258283ecf2a963ac093eb2c7374b876e1aeefdce175f940f78f0efa61
|
3 |
+
size 238048
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 221.7511789811896, "std_reward": 81.24323584120346, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-03T19:36:29.012659"}
|