vivas-1001
commited on
Commit
•
c4c2331
1
Parent(s):
b573408
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 +22 -22
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/pytorch_variables.pth +2 -2
- ppo-LunarLander-v2/system_info.txt +3 -3
- 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: 287.70 +/- 17.53
|
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 0x7e1381a8f370>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e1381a8f400>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e1381a8f490>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e1381a8f520>", "_build": "<function ActorCriticPolicy._build at 0x7e1381a8f5b0>", "forward": "<function ActorCriticPolicy.forward at 0x7e1381a8f640>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e1381a8f6d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e1381a8f760>", "_predict": "<function ActorCriticPolicy._predict at 0x7e1381a8f7f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e1381a8f880>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e1381a8f910>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e1381a8f9a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e1381a91140>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1696697563526299623, "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": 492, "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": 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-5.15.120+-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": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "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 0x7e49534827a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e4953482830>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e49534828c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e4953482950>", "_build": "<function ActorCriticPolicy._build at 0x7e49534829e0>", "forward": "<function ActorCriticPolicy.forward at 0x7e4953482a70>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e4953482b00>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e4953482b90>", "_predict": "<function ActorCriticPolicy._predict at 0x7e4953482c20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e4953482cb0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e4953482d40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e4953482dd0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e495c7dba80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1713550608948612739, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAADPAIL1II526t1souzLh1bhOTkw4z4bLOQAAgD8AAIA/zexuuxQUkLpLIukzF4u4L8QcaLo3Rr6zAACAPwAAgD+aHeE79iBLOzUJ0DxDO5i+91HvO57Dqj0AAAAAAAAAADOOlT0FDoU+a5pHvoYWgb5WVcu9ra7wvAAAAAAAAAAALVEWvpo7KT+mmpw9wQ/PvnkYlb3ieSw9AAAAAAAAAAAAPS69Z3B0PnoJET4fHMe+ayGxPTAkaL0AAAAAAAAAAM2oJ7x2Js0+fjvTvZdLx76Qdpe9lqFGPAAAAAAAAAAATUAAPRTMpLoYyaYvDEVDMQUj3bmKHyAyAACAPwAAgD8a3QI9qtfDPnKfSzyDHMy+4Ht2O3BwyD0AAAAAAAAAAI1Q0T3jU6c+fUZUvmeom75q5NS9ppqOPAAAAAAAAAAAoHOpPt/hmj/YwAk/K9olv13YFD83t4Y9AAAAAAAAAAAzcGU9u1CgPyAGwj7/GQ6//MGGPZM4Xz4AAAAAAAAAAJoIZ71QMkI/0njrPCIkzb7w9oK9OCZlPAAAAAAAAAAAzZjcPEKbbz8kr589Sl7cvkDB/Tw1fPc8AAAAAAAAAADNlFy8nnsIP0CXqD2y+9C+z3NTPZql47sAAAAAAAAAAGb2qLuksSy7ivVRPPKijTxb+om8tRJ0PQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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": 592, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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:eeb679135b65709d95af4810f1513b0686df32a425d2204d347511197a13bdc5
|
3 |
+
size 147968
|
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'>",
|
@@ -41,20 +41,20 @@
|
|
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:": "
|
58 |
"dtype": "float32",
|
59 |
"bounded_below": "[ True True True True True True True True]",
|
60 |
"bounded_above": "[ True True True True True True True True]",
|
@@ -69,7 +69,7 @@
|
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
-
":serialized:": "
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
|
|
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 0x7e49534827a0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e4953482830>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e49534828c0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e4953482950>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7e49534829e0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7e4953482a70>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7e4953482b00>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e4953482b90>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7e4953482c20>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e4953482cb0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e4953482d40>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7e4953482dd0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7e495c7dba80>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1015808,
|
25 |
+
"_total_timesteps": 1000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1713550608948612739,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAADPAIL1II526t1souzLh1bhOTkw4z4bLOQAAgD8AAIA/zexuuxQUkLpLIukzF4u4L8QcaLo3Rr6zAACAPwAAgD+aHeE79iBLOzUJ0DxDO5i+91HvO57Dqj0AAAAAAAAAADOOlT0FDoU+a5pHvoYWgb5WVcu9ra7wvAAAAAAAAAAALVEWvpo7KT+mmpw9wQ/PvnkYlb3ieSw9AAAAAAAAAAAAPS69Z3B0PnoJET4fHMe+ayGxPTAkaL0AAAAAAAAAAM2oJ7x2Js0+fjvTvZdLx76Qdpe9lqFGPAAAAAAAAAAATUAAPRTMpLoYyaYvDEVDMQUj3bmKHyAyAACAPwAAgD8a3QI9qtfDPnKfSzyDHMy+4Ht2O3BwyD0AAAAAAAAAAI1Q0T3jU6c+fUZUvmeom75q5NS9ppqOPAAAAAAAAAAAoHOpPt/hmj/YwAk/K9olv13YFD83t4Y9AAAAAAAAAAAzcGU9u1CgPyAGwj7/GQ6//MGGPZM4Xz4AAAAAAAAAAJoIZ71QMkI/0njrPCIkzb7w9oK9OCZlPAAAAAAAAAAAzZjcPEKbbz8kr589Sl7cvkDB/Tw1fPc8AAAAAAAAAADNlFy8nnsIP0CXqD2y+9C+z3NTPZql47sAAAAAAAAAAGb2qLuksSy7ivVRPPKijTxb+om8tRJ0PQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
|
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": -0.015808000000000044,
|
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": 592,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
"dtype": "float32",
|
59 |
"bounded_below": "[ True True True True True True True True]",
|
60 |
"bounded_above": "[ True True True True True True True True]",
|
|
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
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:ff5e00e1daff45e0bee4196af7ff1f018fee33d8c7b236027150e2e76d7ecde7
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:591816bf98a0ec385949684381663a2750aa97ebddc6d1be111638158e66835d
|
3 |
+
size 43762
|
ppo-LunarLander-v2/pytorch_variables.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 sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
-
- OS: Linux-
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
-
- PyTorch: 2.
|
5 |
- GPU Enabled: True
|
6 |
-
- Numpy: 1.
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.28.1
|
9 |
- OpenAI Gym: 0.25.2
|
|
|
1 |
+
- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.2.1+cu121
|
5 |
- GPU Enabled: True
|
6 |
+
- Numpy: 1.25.2
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.28.1
|
9 |
- OpenAI Gym: 0.25.2
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 287.6973692703956, "std_reward": 17.53045196811069, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-19T18:32:41.062538"}
|