jiang9527li commited on
Commit
ea9a1db
1 Parent(s): bf0c847

Upload PPO LaunchLander train agent

Browse files
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - LunarLander-v2
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: PPO
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: LunarLander-v2
16
+ type: LunarLander-v2
17
+ metrics:
18
+ - type: mean_reward
19
+ value: -55.30 +/- 36.06
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **PPO** Agent playing **LunarLander-v2**
25
+ This is a trained model of a **PPO** agent playing **LunarLander-v2**
26
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
27
+
28
+ ## Usage (with Stable-baselines3)
29
+ TODO: Add your code
30
+
31
+
32
+ ```python
33
+ from stable_baselines3 import ...
34
+ from huggingface_sb3 import load_from_hub
35
+
36
+ ...
37
+ ```
config.json ADDED
@@ -0,0 +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 0x7b59f8cbb370>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b59f8cbb400>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b59f8cbb490>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b59f8cbb520>", "_build": "<function ActorCriticPolicy._build at 0x7b59f8cbb5b0>", "forward": "<function ActorCriticPolicy.forward at 0x7b59f8cbb640>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b59f8cbb6d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b59f8cbb760>", "_predict": "<function ActorCriticPolicy._predict at 0x7b59f8cbb7f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b59f8cbb880>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b59f8cbb910>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b59f8cbb9a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b59f8c67500>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 100352, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1695708780027749470, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADDvZD8uH8+8ckHaunPzB7lcA+497Wr9OQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0035199999999999676, "_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": 784, "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": "Generator(PCG64)"}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWVgQEAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBBfX2dlbmVyYXRvcl9jdG9ylJOUjAVQQ0c2NJSFlFKUfZQojA1iaXRfZ2VuZXJhdG9ylIwFUENHNjSUjAVzdGF0ZZR9lChoI4oROOS0/cmQgKKtx4NxgSPzsACMA2luY5SKEANp7Tpg7f+zJBD8rXVZTGZ1jApoYXNfdWludDMylEsBjAh1aW50ZWdlcpRKcsOINHVidWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "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"}}
ppo-LunarLander-v2.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aca97745412d6dd14d7367e0f7df68009b0c03d07dbadfb97136fff26ccba93f
3
+ size 146573
ppo-LunarLander-v2/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.0.0a5
ppo-LunarLander-v2/data ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
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 0x7b59f8cbb370>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b59f8cbb400>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b59f8cbb490>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b59f8cbb520>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7b59f8cbb5b0>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7b59f8cbb640>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b59f8cbb6d0>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b59f8cbb760>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7b59f8cbb7f0>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b59f8cbb880>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b59f8cbb910>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b59f8cbb9a0>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7b59f8c67500>"
21
+ },
22
+ "verbose": 1,
23
+ "policy_kwargs": {},
24
+ "num_timesteps": 100352,
25
+ "_total_timesteps": 100000,
26
+ "_num_timesteps_at_start": 0,
27
+ "seed": null,
28
+ "action_noise": null,
29
+ "start_time": 1695708780027749470,
30
+ "learning_rate": 0.0003,
31
+ "tensorboard_log": null,
32
+ "_last_obs": {
33
+ ":type:": "<class 'numpy.ndarray'>",
34
+ ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAADDvZD8uH8+8ckHaunPzB7lcA+497Wr9OQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
35
+ },
36
+ "_last_episode_starts": {
37
+ ":type:": "<class 'numpy.ndarray'>",
38
+ ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
39
+ },
40
+ "_last_original_obs": null,
41
+ "_episode_num": 0,
42
+ "use_sde": false,
43
+ "sde_sample_freq": -1,
44
+ "_current_progress_remaining": -0.0035199999999999676,
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": 784,
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]",
61
+ "_shape": [
62
+ 8
63
+ ],
64
+ "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
65
+ "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
66
+ "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
67
+ "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
68
+ "_np_random": "Generator(PCG64)"
69
+ },
70
+ "action_space": {
71
+ ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
72
+ ":serialized:": "gAWVgQEAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBBfX2dlbmVyYXRvcl9jdG9ylJOUjAVQQ0c2NJSFlFKUfZQojA1iaXRfZ2VuZXJhdG9ylIwFUENHNjSUjAVzdGF0ZZR9lChoI4oROOS0/cmQgKKtx4NxgSPzsACMA2luY5SKEANp7Tpg7f+zJBD8rXVZTGZ1jApoYXNfdWludDMylEsBjAh1aW50ZWdlcpRKcsOINHVidWIu",
73
+ "n": "4",
74
+ "start": "0",
75
+ "_shape": [],
76
+ "dtype": "int64",
77
+ "_np_random": "Generator(PCG64)"
78
+ },
79
+ "n_envs": 1,
80
+ "n_steps": 1024,
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": 64,
87
+ "n_epochs": 4,
88
+ "clip_range": {
89
+ ":type:": "<class 'function'>",
90
+ ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
91
+ },
92
+ "clip_range_vf": null,
93
+ "normalize_advantage": true,
94
+ "target_kl": null,
95
+ "lr_schedule": {
96
+ ":type:": "<class 'function'>",
97
+ ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
98
+ }
99
+ }
ppo-LunarLander-v2/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21b6f53c4ebf2dc143c2861e6bf58b3e13d13de38f034009eecf1de55501fcc8
3
+ size 87929
ppo-LunarLander-v2/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24eacb5122a13bff96eb42dbe52bfa12cead4fcc509b9c8dea5e4d2304f54a30
3
+ size 43329
ppo-LunarLander-v2/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
ppo-LunarLander-v2/system_info.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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: 2.0.1+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 (198 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -55.298057299999996, "std_reward": 36.06100748958079, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-26T06:26:44.058597"}