taehoon1lee
commited on
Commit
·
34c4d86
1
Parent(s):
8419f83
Third
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +25 -25
- 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: 260.64 +/- 20.13
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f5b0e512710>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5b0e5127a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5b0e512830>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5b0e5128c0>", "_build": "<function ActorCriticPolicy._build at 0x7f5b0e512950>", "forward": "<function ActorCriticPolicy.forward at 0x7f5b0e5129e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5b0e512a70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5b0e512b00>", "_predict": "<function ActorCriticPolicy._predict at 0x7f5b0e512b90>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5b0e512c20>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5b0e512cb0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5b0e512d40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f5b0e5078c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688135919440752892, "learning_rate": 0.0003, "tensorboard_log": null, "_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": -0.007616000000000067, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 496, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7ff13b344820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff13b3448b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff13b344940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff13b3449d0>", "_build": "<function ActorCriticPolicy._build at 0x7ff13b344a60>", "forward": "<function ActorCriticPolicy.forward at 0x7ff13b344af0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff13b344b80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff13b344c10>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff13b344ca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff13b344d30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff13b344dc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff13b344e50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff13b342f40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2523136, "_total_timesteps": 2500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688190399184307486, "learning_rate": 0.0003, "tensorboard_log": null, "_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": -0.009254400000000107, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 308, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "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": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
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:e3ecb3aa6eb66a7858ebdb9760eb20f0f624893dedc9c4b5a8c4f6e7bf4f0208
|
3 |
+
size 146728
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,34 +4,34 @@
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"num_timesteps":
|
25 |
-
"_total_timesteps":
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -41,17 +41,17 @@
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
-
"_current_progress_remaining": -0.
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
@@ -78,13 +78,13 @@
|
|
78 |
},
|
79 |
"n_envs": 16,
|
80 |
"n_steps": 2048,
|
81 |
-
"gamma": 0.
|
82 |
-
"gae_lambda": 0.
|
83 |
-
"ent_coef": 0.
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
-
"batch_size":
|
87 |
-
"n_epochs":
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":serialized:": "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"
|
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7ff13b344820>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff13b3448b0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff13b344940>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff13b3449d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7ff13b344a60>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7ff13b344af0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff13b344b80>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff13b344c10>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7ff13b344ca0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff13b344d30>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff13b344dc0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff13b344e50>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7ff13b342f40>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 2523136,
|
25 |
+
"_total_timesteps": 2500000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1688190399184307486,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.009254400000000107,
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 308,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
|
|
|
78 |
},
|
79 |
"n_envs": 16,
|
80 |
"n_steps": 2048,
|
81 |
+
"gamma": 0.999,
|
82 |
+
"gae_lambda": 0.98,
|
83 |
+
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 128,
|
87 |
+
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":serialized:": "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"
|
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 sha256:208fb77dccfb0729706798801a6ad3e7a10789b22a97bd954f74752060f5e187
|
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 43329
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2194c454d6830d8aa3dc35aac6ce24fb0688599edf8922810fc2913d36b6a71c
|
3 |
size 43329
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 260.6369702, "std_reward": 20.134625989076287, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-01T06:30:55.574391"}
|