dodge99 commited on
Commit
196e1ec
1 Parent(s): 9107c7a

Initial commit

Browse files
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - AntBulletEnv-v0
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: A2C
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: AntBulletEnv-v0
16
+ type: AntBulletEnv-v0
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 376.30 +/- 46.89
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **A2C** Agent playing **AntBulletEnv-v0**
25
+ This is a trained model of a **A2C** agent playing **AntBulletEnv-v0**
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
+ ```
a2c-AntBulletEnv-v0.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57c4bf35d29d2ed9e04d24e53e8655e2e0e1e7d63b7e3a0c11bb2c9372d4cccf
3
+ size 125108
a2c-AntBulletEnv-v0/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.6.2
a2c-AntBulletEnv-v0/data ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
5
+ "__module__": "stable_baselines3.common.policies",
6
+ "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
7
+ "__init__": "<function ActorCriticPolicy.__init__ at 0x7f7e91d5fef0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7e91d5ff80>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7e91d68050>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7e91d680e0>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f7e91d68170>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f7e91d68200>",
13
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7e91d68290>",
14
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f7e91d68320>",
15
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7e91d683b0>",
16
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7e91d68440>",
17
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7e91d684d0>",
18
+ "__abstractmethods__": "frozenset()",
19
+ "_abc_impl": "<_abc_data object at 0x7f7e91da2de0>"
20
+ },
21
+ "verbose": 1,
22
+ "policy_kwargs": {
23
+ ":type:": "<class 'dict'>",
24
+ ":serialized:": "gASVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu",
25
+ "log_std_init": -2,
26
+ "ortho_init": false,
27
+ "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
28
+ "optimizer_kwargs": {
29
+ "alpha": 0.99,
30
+ "eps": 1e-05,
31
+ "weight_decay": 0
32
+ }
33
+ },
34
+ "observation_space": {
35
+ ":type:": "<class 'gym.spaces.box.Box'>",
36
+ ":serialized:": "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",
37
+ "dtype": "float32",
38
+ "_shape": [
39
+ 28
40
+ ],
41
+ "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
42
+ "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf]",
43
+ "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]",
44
+ "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]",
45
+ "_np_random": null
46
+ },
47
+ "action_space": {
48
+ ":type:": "<class 'gym.spaces.box.Box'>",
49
+ ":serialized:": "gASVwwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBVudW1weS5jb3JlLm11bHRpYXJyYXmUjAxfcmVjb25zdHJ1Y3SUk5RoBowHbmRhcnJheZSTlEsAhZRDAWKUh5RSlChLAUsIhZRoColDIAAAgL8AAIC/AACAvwAAgL8AAIC/AACAvwAAgL8AAIC/lHSUYowEaGlnaJRoEmgUSwCFlGgWh5RSlChLAUsIhZRoColDIAAAgD8AAIA/AACAPwAAgD8AAIA/AACAPwAAgD8AAIA/lHSUYowNYm91bmRlZF9iZWxvd5RoEmgUSwCFlGgWh5RSlChLAUsIhZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDCAEBAQEBAQEBlHSUYowNYm91bmRlZF9hYm92ZZRoEmgUSwCFlGgWh5RSlChLAUsIhZRoKolDCAEBAQEBAQEBlHSUYowKX25wX3JhbmRvbZROdWIu",
50
+ "dtype": "float32",
51
+ "_shape": [
52
+ 8
53
+ ],
54
+ "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
55
+ "high": "[1. 1. 1. 1. 1. 1. 1. 1.]",
56
+ "bounded_below": "[ True True True True True True True True]",
57
+ "bounded_above": "[ True True True True True True True True]",
58
+ "_np_random": null
59
+ },
60
+ "n_envs": 4,
61
+ "num_timesteps": 1024,
62
+ "_total_timesteps": 1000,
63
+ "_num_timesteps_at_start": 0,
64
+ "seed": null,
65
+ "action_noise": null,
66
+ "start_time": 1668007964742022040,
67
+ "learning_rate": 0.00096,
68
+ "tensorboard_log": "./tensorboard",
69
+ "lr_schedule": {
70
+ ":type:": "<class 'function'>",
71
+ ":serialized:": "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"
72
+ },
73
+ "_last_obs": {
74
+ ":type:": "<class 'numpy.ndarray'>",
75
+ ":serialized:": "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"
76
+ },
77
+ "_last_episode_starts": {
78
+ ":type:": "<class 'numpy.ndarray'>",
79
+ ":serialized:": "gASVjAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwSFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDBAAAAACUdJRiLg=="
80
+ },
81
+ "_last_original_obs": {
82
+ ":type:": "<class 'numpy.ndarray'>",
83
+ ":serialized:": "gASVTQIAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwRLHIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiULAAQAAAAAAAPA3D7cAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIArfPg9AAAAACvYAMAAAAAAcHXfvQAAAADcuvM/AAAAAI/tgbwAAAAAJoztPwAAAABpvhA+AAAAAKp62r8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA+AuE2AACAPwAAAAAAAAAAAAAAAAAAAAAAAACASFYFvgAAAABSy/y/AAAAAOVMDz4AAAAAS/HvPwAAAADobQA+AAAAADsY7j8AAAAA2MnFPQAAAADgcNq/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADFuJNgAAgD8AAAAAAAAAAAAAAAAAAAAAAAAAgOMOCr4AAAAAHPLxvwAAAAASE108AAAAAI4M4D8AAAAAgumfPQAAAAC53P0/AAAAAE+2OD0AAAAA9enrvwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJS71rUAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIBc4c88AAAAAOkeAMAAAAAAkHDKvAAAAADDj+w/AAAAAKQQWb0AAAAAZuPePwAAAADn4gS9AAAAAMIl/b8AAAAAAAAAAAAAAAAAAAAAAAAAAJR0lGIu"
84
+ },
85
+ "_episode_num": 0,
86
+ "use_sde": true,
87
+ "sde_sample_freq": -1,
88
+ "_current_progress_remaining": -0.02400000000000002,
89
+ "ep_info_buffer": {
90
+ ":type:": "<class 'collections.deque'>",
91
+ ":serialized:": "gASVRQAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUfZQojAFylEdACiXY150KZ4wBbJRLFYwBdJRHQEAJf1pTMq11YS4="
92
+ },
93
+ "ep_success_buffer": {
94
+ ":type:": "<class 'collections.deque'>",
95
+ ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
96
+ },
97
+ "_n_updates": 133,
98
+ "n_steps": 8,
99
+ "gamma": 0.99,
100
+ "gae_lambda": 0.9,
101
+ "ent_coef": 0.0,
102
+ "vf_coef": 0.4,
103
+ "max_grad_norm": 0.5,
104
+ "normalize_advantage": false
105
+ }
a2c-AntBulletEnv-v0/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c1c67af752ad018435575de3961ffa02b73e5ba1927af220f3f33d1080199a
3
+ size 56126
a2c-AntBulletEnv-v0/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2535152093b1683730f0a007036fcbd3ea468d0c20a7d281c8ce2acaba4f79cb
3
+ size 56766
a2c-AntBulletEnv-v0/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
a2c-AntBulletEnv-v0/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ OS: Linux-5.10.133+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022
2
+ Python: 3.7.15
3
+ Stable-Baselines3: 1.6.2
4
+ PyTorch: 1.12.1+cu113
5
+ GPU Enabled: True
6
+ Numpy: 1.21.6
7
+ Gym: 0.21.0
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f7e91d5fef0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7e91d5ff80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7e91d68050>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7e91d680e0>", "_build": "<function ActorCriticPolicy._build at 0x7f7e91d68170>", "forward": "<function ActorCriticPolicy.forward at 0x7f7e91d68200>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7e91d68290>", "_predict": "<function ActorCriticPolicy._predict at 0x7f7e91d68320>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7e91d683b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7e91d68440>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7e91d684d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f7e91da2de0>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gASVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu", "log_std_init": -2, "ortho_init": false, "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [28], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_np_random": null}, "n_envs": 4, "num_timesteps": 1024, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1668007964742022040, "learning_rate": 0.00096, "tensorboard_log": "./tensorboard", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gASVwQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjEgvdXNyL2xvY2FsL2xpYi9weXRob24zLjcvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuAQwIAAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEgvdXNyL2xvY2FsL2xpYi9weXRob24zLjcvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP091EE1VHWmFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVTQIAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwRLHIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiULAAQAAzQ+ePyniwj0j7zY/7sRKvYszYj3xDmk+kKIEPmRkkb+S0eA+wun9vDdvAkBlv7C9FUIsP5H+vLyWs1Y/YlSDPSamgr99CJg8KFEuP2dIYD2yqoW/X8TpPF1c2T8POcS92VHLPnFO1T5uMf0+bnSxPmYsHL88H9u92HFEPwnrgTwFeEM9XrNGPufp6D/1EFvArjfiPs1oirxDUAJAz2kLvszJEsDVqWW8GxkDPswJgz2dVq4/LbYUPfOB2T+j9J09qqmFv+sJ+T1Ubtk/j6CMvTMqIcBxTtU+bjH9Pm50sT6oKje/eqsOwJhcG8AkhoK9lmBqPen6az7argI+lKGsPlHdSsAo8oq8vIz2vruuu72BUhLAm3+KvKp1Cz7ID4M93wh5v+NuyTwXFHE9275QPZARN79feQo9dWsPv9J3vb3ZUcs+cU7VPm4x/T5udLE+Lsm/Pz12oT63TRc/Ud6xvRbaFj7Dz2w+C0GIPQT0Tb+74OI+DACnvSpbAkDHxI+90WoiPxEKL7zhfgw+PRYJPFY/gr+iKT87DaI0PbM9CT2qn4W/5jVcPSyXyz9QW9m92VHLPnFO1T5uMf0+bnSxPpR0lGIu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVjAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwSFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDBAAAAACUdJRiLg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 0, "use_sde": true, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVRQAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUfZQojAFylEdACiXY150KZ4wBbJRLFYwBdJRHQEAJf1pTMq11YS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 133, "n_steps": 8, "gamma": 0.99, "gae_lambda": 0.9, "ent_coef": 0.0, "vf_coef": 0.4, "max_grad_norm": 0.5, "normalize_advantage": false, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.7.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
replay.mp4 ADDED
Binary file (163 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 376.300827701902, "std_reward": 46.885249469037774, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-11-09T15:34:51.263365"}
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f2e03f2ff28d8d1712df4abe4a0792e4d38a72f7727f1e4fb2504bb49199739
3
+ size 2763