josef-o commited on
Commit
b617ce0
1 Parent(s): be0a367

Initial commit

Browse files
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - PandaReachDense-v3
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: PandaReachDense-v3
16
+ type: PandaReachDense-v3
17
+ metrics:
18
+ - type: mean_reward
19
+ value: -0.25 +/- 0.17
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **A2C** Agent playing **PandaReachDense-v3**
25
+ This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
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-panda-rlcourse.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0dfc7d6969d9da24039390e34bd970df093f49d7dc6d92b5b84699e2a6c4bf
3
+ size 106828
a2c-panda-rlcourse/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.1.0
a2c-panda-rlcourse/data ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=",
5
+ "__module__": "stable_baselines3.common.policies",
6
+ "__doc__": "\n MultiInputActorClass 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 (Tuple)\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: Uses the CombinedExtractor\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 MultiInputActorCriticPolicy.__init__ at 0x7c9ddb490c10>",
8
+ "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7c9ddb485f80>"
10
+ },
11
+ "verbose": 1,
12
+ "policy_kwargs": {
13
+ ":type:": "<class 'dict'>",
14
+ ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=",
15
+ "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
16
+ "optimizer_kwargs": {
17
+ "alpha": 0.99,
18
+ "eps": 1e-05,
19
+ "weight_decay": 0
20
+ }
21
+ },
22
+ "num_timesteps": 100000,
23
+ "_total_timesteps": 100000,
24
+ "_num_timesteps_at_start": 0,
25
+ "seed": null,
26
+ "action_noise": null,
27
+ "start_time": 1693586467843371913,
28
+ "learning_rate": 0.0007,
29
+ "tensorboard_log": null,
30
+ "_last_obs": {
31
+ ":type:": "<class 'collections.OrderedDict'>",
32
+ ":serialized:": "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",
33
+ "achieved_goal": "[[ 0.1425577 -0.03491564 0.40633166]\n [ 0.1425577 -0.03491564 0.40633166]\n [-0.8195399 0.66955644 0.5422188 ]\n [ 0.1425577 -0.03491564 0.40633166]]",
34
+ "desired_goal": "[[-1.3462728 -0.05936343 -0.8936492 ]\n [-0.32071626 0.1256683 0.10352874]\n [-1.1763175 1.027531 0.9965003 ]\n [ 0.11269818 -1.0775706 -1.0871216 ]]",
35
+ "observation": "[[ 0.1425577 -0.03491564 0.40633166 0.32854158 -0.00706776 0.26581758]\n [ 0.1425577 -0.03491564 0.40633166 0.32854158 -0.00706776 0.26581758]\n [-0.8195399 0.66955644 0.5422188 -1.0337381 1.1390585 1.5001308 ]\n [ 0.1425577 -0.03491564 0.40633166 0.32854158 -0.00706776 0.26581758]]"
36
+ },
37
+ "_last_episode_starts": {
38
+ ":type:": "<class 'numpy.ndarray'>",
39
+ ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
40
+ },
41
+ "_last_original_obs": {
42
+ ":type:": "<class 'collections.OrderedDict'>",
43
+ ":serialized:": "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",
44
+ "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]",
45
+ "desired_goal": "[[-0.14321482 -0.02406669 0.0483035 ]\n [-0.0738882 -0.00542262 0.11375668]\n [ 0.01795167 0.00179663 0.03578729]\n [ 0.0767708 -0.09152773 0.03152015]]",
46
+ "observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"
47
+ },
48
+ "_episode_num": 0,
49
+ "use_sde": false,
50
+ "sde_sample_freq": -1,
51
+ "_current_progress_remaining": 0.0,
52
+ "_stats_window_size": 100,
53
+ "ep_info_buffer": {
54
+ ":type:": "<class 'collections.deque'>",
55
+ ":serialized:": "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"
56
+ },
57
+ "ep_success_buffer": {
58
+ ":type:": "<class 'collections.deque'>",
59
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
60
+ },
61
+ "_n_updates": 5500,
62
+ "n_steps": 5,
63
+ "gamma": 0.99,
64
+ "gae_lambda": 1.0,
65
+ "ent_coef": 0.0,
66
+ "vf_coef": 0.5,
67
+ "max_grad_norm": 0.5,
68
+ "normalize_advantage": false,
69
+ "observation_space": {
70
+ ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
71
+ ":serialized:": "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",
72
+ "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])",
73
+ "_shape": null,
74
+ "dtype": null,
75
+ "_np_random": null
76
+ },
77
+ "action_space": {
78
+ ":type:": "<class 'gymnasium.spaces.box.Box'>",
79
+ ":serialized:": "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",
80
+ "dtype": "float32",
81
+ "bounded_below": "[ True True True]",
82
+ "bounded_above": "[ True True True]",
83
+ "_shape": [
84
+ 3
85
+ ],
86
+ "low": "[-1. -1. -1.]",
87
+ "high": "[1. 1. 1.]",
88
+ "low_repr": "-1.0",
89
+ "high_repr": "1.0",
90
+ "_np_random": null
91
+ },
92
+ "n_envs": 4,
93
+ "lr_schedule": {
94
+ ":type:": "<class 'function'>",
95
+ ":serialized:": "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"
96
+ }
97
+ }
a2c-panda-rlcourse/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dab14a6e415c176e9c8d6719eb264735b4a8eacf78ae2c4cdd1f39b8cb76d64
3
+ size 44734
a2c-panda-rlcourse/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e10a833cadca19513fa7b6f3627a90f0e4bd72a79ef84d8bad66b05d1e6a6f
3
+ size 46014
a2c-panda-rlcourse/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-panda-rlcourse/system_info.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
2
+ - Python: 3.10.12
3
+ - Stable-Baselines3: 2.1.0
4
+ - PyTorch: 2.0.1+cu118
5
+ - GPU Enabled: True
6
+ - Numpy: 1.23.5
7
+ - Cloudpickle: 2.2.1
8
+ - Gymnasium: 0.29.1
9
+ - OpenAI Gym: 0.25.2
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n MultiInputActorClass 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 (Tuple)\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: Uses the CombinedExtractor\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 MultiInputActorCriticPolicy.__init__ at 0x7c9ddb490c10>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c9ddb485f80>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 100000, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1693586467843371913, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.1425577 -0.03491564 0.40633166]\n [ 0.1425577 -0.03491564 0.40633166]\n [-0.8195399 0.66955644 0.5422188 ]\n [ 0.1425577 -0.03491564 0.40633166]]", "desired_goal": "[[-1.3462728 -0.05936343 -0.8936492 ]\n [-0.32071626 0.1256683 0.10352874]\n [-1.1763175 1.027531 0.9965003 ]\n [ 0.11269818 -1.0775706 -1.0871216 ]]", "observation": "[[ 0.1425577 -0.03491564 0.40633166 0.32854158 -0.00706776 0.26581758]\n [ 0.1425577 -0.03491564 0.40633166 0.32854158 -0.00706776 0.26581758]\n [-0.8195399 0.66955644 0.5422188 -1.0337381 1.1390585 1.5001308 ]\n [ 0.1425577 -0.03491564 0.40633166 0.32854158 -0.00706776 0.26581758]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]", "desired_goal": "[[-0.14321482 -0.02406669 0.0483035 ]\n [-0.0738882 -0.00542262 0.11375668]\n [ 0.01795167 0.00179663 0.03578729]\n [ 0.0767708 -0.09152773 0.03152015]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_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": 5500, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
replay.mp4 ADDED
Binary file (735 kB). View file
 
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -0.2469809495843947, "std_reward": 0.1741965120030135, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-01T16:48:19.736072"}
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85cd77646a7ca011e2c7bb0b05b821dd5926d3ea0efc5d9210e8f2dc8032194a
3
+ size 2636