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 +2 -2
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
README.md
CHANGED
@@ -10,7 +10,7 @@ model-index:
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
-
value:
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 227.63 +/- 40.05
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
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 0x7ff9dceb4c20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff9dceb4cb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff9dceb4d40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff9dceb4dd0>", "_build": "<function ActorCriticPolicy._build at 0x7ff9dceb4e60>", "forward": "<function ActorCriticPolicy.forward at 0x7ff9dceb4ef0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff9dceb4f80>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff9dcebc050>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff9dcebc0e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff9dcebc170>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff9dcebc200>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7ff9dce8a540>"}, "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651865142.598179, "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": 124, "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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "False", "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 0x7f8f0579a170>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8f0579a200>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8f0579a290>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8f0579a320>", "_build": "<function ActorCriticPolicy._build at 0x7f8f0579a3b0>", "forward": "<function ActorCriticPolicy.forward at 0x7f8f0579a440>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8f0579a4d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8f0579a560>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8f0579a5f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8f0579a680>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8f0579a710>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f8f057e1b10>"}, "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": 901120, "_total_timesteps": 900000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651872522.8621097, "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": -0.0012444444444443814, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 330, "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": 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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "False", "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 sha256:47e2e441b0403d106ff752916a0c31fe019e5f3f5d61d5807b0d3d3bfb698c5d
|
3 |
+
size 143730
|
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'>",
|
@@ -66,16 +66,16 @@
|
|
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": 0.999,
|
81 |
"gae_lambda": 0.98,
|
@@ -83,7 +83,7 @@
|
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
"batch_size": 64,
|
86 |
-
"n_epochs":
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
|
|
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 0x7f8f0579a170>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8f0579a200>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8f0579a290>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8f0579a320>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f8f0579a3b0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f8f0579a440>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8f0579a4d0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f8f0579a560>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8f0579a5f0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8f0579a680>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8f0579a710>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f8f057e1b10>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 901120,
|
46 |
+
"_total_timesteps": 900000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1651872522.8621097,
|
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": -0.0012444444444443814,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 330,
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
|
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
"batch_size": 64,
|
86 |
+
"n_epochs": 6,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbb17e318ec87230d3e72141c91cb59bbd9161e8e0ac8e4445e7a08a2f2a649c
|
3 |
+
size 84637
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43073
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbf8e3b26de63220fec2ba093741e62dce18f8a1343c7243c0e338a906ee9b90
|
3 |
size 43073
|
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 sha256:544ed25a38449d935cb14dddd01c9eb7de8cf362abb02bc25feb7bd70822401e
|
3 |
+
size 243595
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 227.62877981930396, "std_reward": 40.05066285349392, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T22:37:08.486686"}
|