ppo_lunar_09_back_to_best
Browse files- README.md +2 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +21 -21
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +1 -1
- ppo-LunarLander-v2/system_info.txt +1 -1
- 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
|
@@ -27,6 +27,7 @@ model-index:
|
|
27 |
|
28 |
|
29 |
|
|
|
30 |
# **PPO** Agent playing **LunarLander-v2**
|
31 |
This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
32 |
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 268.36 +/- 12.39
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
27 |
|
28 |
|
29 |
|
30 |
+
|
31 |
# **PPO** Agent playing **LunarLander-v2**
|
32 |
This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
33 |
|
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 0x000002172C9FB700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000002172C9FB790>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000002172C9FB820>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000002172C9FB8B0>", "_build": "<function ActorCriticPolicy._build at 0x000002172C9FB940>", "forward": "<function ActorCriticPolicy.forward at 0x000002172C9FB9D0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000002172C9FBA60>", "_predict": "<function ActorCriticPolicy._predict at 0x000002172C9FBAF0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000002172C9FBB80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000002172C9FBC10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000002172C9FBCA0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x000002172C9F5840>"}, "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": 16384, "_total_timesteps": 500, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651864706.0585933, "learning_rate": 0.0003, "tensorboard_log": "D:\\tmp\\tf", "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": -31.768, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 5, "n_steps": 1024, "gamma": 0.98, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 5, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Windows-10-10.0.22610-SP0 10.0.22610", "Python": "3.8.10", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.22.3", "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 0x000001D058C6B700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001D058C6B790>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001D058C6B820>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001D058C6B8B0>", "_build": "<function ActorCriticPolicy._build at 0x000001D058C6B940>", "forward": "<function ActorCriticPolicy.forward at 0x000001D058C6B9D0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001D058C6BA60>", "_predict": "<function ActorCriticPolicy._predict at 0x000001D058C6BAF0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001D058C6BB80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001D058C6BC10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001D058C6BCA0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x000001D058C68840>"}, "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": 1802240, "_total_timesteps": 1800000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651914524.2168138, "learning_rate": 0.0003, "tensorboard_log": "D:\\tmp\\tf", "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": 550, "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": 128, "n_epochs": 5, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Windows-10-10.0.22616-SP0 10.0.22616", "Python": "3.8.10", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.22.3", "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 sha256:1381f37f7aa3be5ce4f6fa73dedb5cfbd99e57be27782e8b13bb170bfea35a5b
|
3 |
+
size 143851
|
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": "D:\\tmp\\tf",
|
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'>",
|
@@ -66,23 +66,23 @@
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining": -
|
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,
|
84 |
"max_grad_norm": 0.5,
|
85 |
-
"batch_size":
|
86 |
"n_epochs": 5,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
|
|
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 0x000001D058C6B700>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001D058C6B790>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001D058C6B820>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001D058C6B8B0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x000001D058C6B940>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x000001D058C6B9D0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001D058C6BA60>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x000001D058C6BAF0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001D058C6BB80>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001D058C6BC10>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x000001D058C6BCA0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x000001D058C68840>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 1802240,
|
46 |
+
"_total_timesteps": 1800000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1651914524.2168138,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": "D:\\tmp\\tf",
|
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": 550,
|
79 |
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 128,
|
86 |
"n_epochs": 5,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
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 sha256:1be2c52a7772977b497dbd8e18d1e1d91abefcc399542338dc800f5b198c84c0
|
3 |
+
size 84893
|
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 sha256:5da4308ab6aeddacf286e13035a23a0bc1e79d94a733d9699e58135612908e5e
|
3 |
size 43201
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
OS: Windows-10-10.0.
|
2 |
Python: 3.8.10
|
3 |
Stable-Baselines3: 1.5.0
|
4 |
PyTorch: 1.11.0+cu113
|
|
|
1 |
+
OS: Windows-10-10.0.22616-SP0 10.0.22616
|
2 |
Python: 3.8.10
|
3 |
Stable-Baselines3: 1.5.0
|
4 |
PyTorch: 1.11.0+cu113
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 268.3573923440396, "std_reward": 12.389831559846417, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-07T10:42:49.557202"}
|