michael-kingston
commited on
Commit
·
66215c4
1
Parent(s):
1184156
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 +19 -19
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- ppo-LunarLander-v2/system_info.txt +5 -4
- 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: 158.20 +/- 83.43
|
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 0x7f92f2650820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f92f26508b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f92f2650940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f92f26509d0>", "_build": "<function ActorCriticPolicy._build at 0x7f92f2650a60>", "forward": "<function ActorCriticPolicy.forward at 0x7f92f2650af0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f92f2650b80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f92f2650c10>", "_predict": "<function ActorCriticPolicy._predict at 0x7f92f2650ca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f92f2650d30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f92f2650dc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f92f2650e50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f92f263bac0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1698199332610748375, "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": -0.015808000000000044, "_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": 248, "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-6.5.6-76060506-generic-x86_64-with-glibc2.35 # 202310061235~1697396945~22.04~9283e32 SMP PREEMPT_DYNAMIC Sun O", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}
|
|
|
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 0x7904f7501360>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7904f75013f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7904f7501480>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7904f7501510>", "_build": "<function ActorCriticPolicy._build at 0x7904f75015a0>", "forward": "<function ActorCriticPolicy.forward at 0x7904f7501630>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7904f75016c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7904f7501750>", "_predict": "<function ActorCriticPolicy._predict at 0x7904f75017e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7904f7501870>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7904f7501900>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7904f7501990>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7904f74fcd00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1698200629693153580, "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": -0.015808000000000044, "_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": 248, "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": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 256, "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-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "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 sha256:51fb28ff4d49043faa9f4d17d56a282b72230296d1b4767563395c2bd3c893cd
|
3 |
+
size 148059
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,20 +4,20 @@
|
|
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": {},
|
@@ -26,12 +26,12 @@
|
|
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'>",
|
@@ -45,7 +45,7 @@
|
|
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'>",
|
@@ -83,17 +83,17 @@
|
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
-
"batch_size":
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
-
":serialized:": "
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
"target_kl": null,
|
95 |
"lr_schedule": {
|
96 |
":type:": "<class 'function'>",
|
97 |
-
":serialized:": "
|
98 |
}
|
99 |
}
|
|
|
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 0x7904f7501360>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7904f75013f0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7904f7501480>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7904f7501510>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7904f75015a0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7904f7501630>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7904f75016c0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7904f7501750>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7904f75017e0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7904f7501870>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7904f7501900>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7904f7501990>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7904f74fcd00>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1698200629693153580,
|
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'>",
|
|
|
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'>",
|
|
|
83 |
"ent_coef": 0.01,
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 256,
|
87 |
"n_epochs": 4,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "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"
|
91 |
},
|
92 |
"clip_range_vf": null,
|
93 |
"normalize_advantage": true,
|
94 |
"target_kl": null,
|
95 |
"lr_schedule": {
|
96 |
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
}
|
99 |
}
|
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 88362
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3618a2ed7ffe509300fb031cff37777434c89a2852ca00ddbeaac506f726902
|
3 |
size 88362
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eb2e0df5b73326565f74845eedfe506c34cdd7953eec6505905cf444719e0fe
|
3 |
size 43762
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
-
- OS: Linux-
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
-
- PyTorch: 2.1.0
|
5 |
- GPU Enabled: True
|
6 |
-
- Numpy: 1.
|
7 |
-
- Cloudpickle:
|
8 |
- Gymnasium: 0.28.1
|
|
|
|
1 |
+
- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.1.0+cu118
|
5 |
- GPU Enabled: True
|
6 |
+
- Numpy: 1.23.5
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
ADDED
Binary file (205 kB). View file
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 158.19822241674052, "std_reward": 83.43303751555945, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-25T02:50:30.787808"}
|