Quentin Gallouédec commited on
Commit
c8d0213
1 Parent(s): 3dd6f30

Initial commit

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - PandaReach-v1
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: TQC
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: PandaReach-v1
16
+ type: PandaReach-v1
17
+ metrics:
18
+ - type: mean_reward
19
+ value: -2.00 +/- 0.77
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **TQC** Agent playing **PandaReach-v1**
25
+ This is a trained model of a **TQC** agent playing **PandaReach-v1**
26
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
27
+ and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
28
+
29
+ The RL Zoo is a training framework for Stable Baselines3
30
+ reinforcement learning agents,
31
+ with hyperparameter optimization and pre-trained agents included.
32
+
33
+ ## Usage (with SB3 RL Zoo)
34
+
35
+ RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
36
+ SB3: https://github.com/DLR-RM/stable-baselines3<br/>
37
+ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
38
+
39
+ Install the RL Zoo (with SB3 and SB3-Contrib):
40
+ ```bash
41
+ pip install rl_zoo3
42
+ ```
43
+
44
+ ```
45
+ # Download model and save it into the logs/ folder
46
+ python -m rl_zoo3.load_from_hub --algo tqc --env PandaReach-v1 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo tqc --env PandaReach-v1 -f logs/
48
+ ```
49
+
50
+ If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
51
+ ```
52
+ python -m rl_zoo3.load_from_hub --algo tqc --env PandaReach-v1 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo tqc --env PandaReach-v1 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo tqc --env PandaReach-v1 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo tqc --env PandaReach-v1 -f logs/ -orga qgallouedec
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('batch_size', 256),
66
+ ('buffer_size', 1000000),
67
+ ('ent_coef', 'auto'),
68
+ ('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
69
+ ('gamma', 0.95),
70
+ ('gradient_steps', -1),
71
+ ('learning_rate', 0.001),
72
+ ('learning_starts', 1000),
73
+ ('n_envs', 8),
74
+ ('n_timesteps', 20000.0),
75
+ ('normalize', True),
76
+ ('policy', 'MultiInputPolicy'),
77
+ ('policy_kwargs', 'dict(net_arch=[64, 64], n_critics=1)'),
78
+ ('replay_buffer_class', 'HerReplayBuffer'),
79
+ ('replay_buffer_kwargs',
80
+ "dict( online_sampling=True, goal_selection_strategy='future', "
81
+ 'n_sampled_goal=4 )'),
82
+ ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
83
+ ```
84
+
85
+ # Environment Arguments
86
+ ```python
87
+ {'render': True}
88
+ ```
args.yml ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - tqc
4
+ - - conf_file
5
+ - null
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - PandaReach-v1
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_episodes
13
+ - 20
14
+ - - eval_freq
15
+ - 25000
16
+ - - gym_packages
17
+ - []
18
+ - - hyperparams
19
+ - n_envs: 8
20
+ - - log_folder
21
+ - logs
22
+ - - log_interval
23
+ - -1
24
+ - - max_total_trials
25
+ - null
26
+ - - n_eval_envs
27
+ - 5
28
+ - - n_evaluations
29
+ - null
30
+ - - n_jobs
31
+ - 1
32
+ - - n_startup_trials
33
+ - 10
34
+ - - n_timesteps
35
+ - -1
36
+ - - n_trials
37
+ - 500
38
+ - - no_optim_plots
39
+ - false
40
+ - - num_threads
41
+ - -1
42
+ - - optimization_log_path
43
+ - null
44
+ - - optimize_hyperparameters
45
+ - false
46
+ - - progress
47
+ - false
48
+ - - pruner
49
+ - median
50
+ - - sampler
51
+ - tpe
52
+ - - save_freq
53
+ - -1
54
+ - - save_replay_buffer
55
+ - false
56
+ - - seed
57
+ - 750406541
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - runs/PandaReach-v1__tqc__750406541__1676298577
64
+ - - track
65
+ - true
66
+ - - trained_agent
67
+ - ''
68
+ - - truncate_last_trajectory
69
+ - true
70
+ - - uuid
71
+ - false
72
+ - - vec_env
73
+ - dummy
74
+ - - verbose
75
+ - 1
76
+ - - wandb_entity
77
+ - qgallouedec
78
+ - - wandb_project_name
79
+ - vec-her-sb3
80
+ - - wandb_tags
81
+ - []
82
+ - - yaml_file
83
+ - null
config.yml ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 256
4
+ - - buffer_size
5
+ - 1000000
6
+ - - ent_coef
7
+ - auto
8
+ - - env_wrapper
9
+ - sb3_contrib.common.wrappers.TimeFeatureWrapper
10
+ - - gamma
11
+ - 0.95
12
+ - - gradient_steps
13
+ - -1
14
+ - - learning_rate
15
+ - 0.001
16
+ - - learning_starts
17
+ - 1000
18
+ - - n_envs
19
+ - 8
20
+ - - n_timesteps
21
+ - 20000.0
22
+ - - normalize
23
+ - true
24
+ - - policy
25
+ - MultiInputPolicy
26
+ - - policy_kwargs
27
+ - dict(net_arch=[64, 64], n_critics=1)
28
+ - - replay_buffer_class
29
+ - HerReplayBuffer
30
+ - - replay_buffer_kwargs
31
+ - dict( online_sampling=True, goal_selection_strategy='future', n_sampled_goal=4
32
+ )
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ render: true
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b85f8e2bddd6983d05428ac62403f5f786d989c52ad054e263e92c34b0f7b52b
3
+ size 603661
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -2.0, "std_reward": 0.7745966692414834, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T16:55:31.812586"}
tqc-PandaReach-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b2dd3341a97bf2a91fb1f233a1ba8bd9a8f03971d9ed1ff79710b7bd04c436
3
+ size 225612
tqc-PandaReach-v1/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.8.0a6
tqc-PandaReach-v1/actor.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5a59652ef64878e69a4b65b4f699a896cdea68d382998ac22e4914424b4af8b
3
+ size 50077
tqc-PandaReach-v1/critic.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6800b17440e2a6a641af6e258c5ee31b42dba601d658126a3c711bd40101ff7b
3
+ size 59951
tqc-PandaReach-v1/data ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gAWVMQAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
5
+ "__module__": "sb3_contrib.tqc.policies",
6
+ "__doc__": "\n Policy class (with both actor and critic) for TQC.\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 use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n :param features_extractor_class: Features extractor to use.\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 :param n_quantiles: Number of quantiles for the critic.\n :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ",
7
+ "__init__": "<function MultiInputPolicy.__init__ at 0x7f20c3123a60>",
8
+ "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7f20c3124880>"
10
+ },
11
+ "verbose": 1,
12
+ "policy_kwargs": {
13
+ "net_arch": [
14
+ 64,
15
+ 64
16
+ ],
17
+ "n_critics": 1,
18
+ "use_sde": false
19
+ },
20
+ "observation_space": {
21
+ ":type:": "<class 'gym.spaces.dict.Dict'>",
22
+ ":serialized:": "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",
23
+ "spaces": "OrderedDict([('achieved_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('desired_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('observation', Box([-10. -10. -10. -10. -10. -10. 0.], [10. 10. 10. 10. 10. 10. 1.], (7,), float32))])",
24
+ "_shape": null,
25
+ "dtype": null,
26
+ "_np_random": null
27
+ },
28
+ "action_space": {
29
+ ":type:": "<class 'gym.spaces.box.Box'>",
30
+ ":serialized:": "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",
31
+ "dtype": "float32",
32
+ "_shape": [
33
+ 3
34
+ ],
35
+ "low": "[-1. -1. -1.]",
36
+ "high": "[1. 1. 1.]",
37
+ "bounded_below": "[ True True True]",
38
+ "bounded_above": "[ True True True]",
39
+ "_np_random": "RandomState(MT19937)"
40
+ },
41
+ "n_envs": 1,
42
+ "num_timesteps": 20000,
43
+ "_total_timesteps": 20000,
44
+ "_num_timesteps_at_start": 0,
45
+ "seed": 0,
46
+ "action_noise": null,
47
+ "start_time": 1676298581602906179,
48
+ "learning_rate": {
49
+ ":type:": "<class 'function'>",
50
+ ":serialized:": "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"
51
+ },
52
+ "tensorboard_log": "runs/PandaReach-v1__tqc__750406541__1676298577/PandaReach-v1",
53
+ "lr_schedule": {
54
+ ":type:": "<class 'function'>",
55
+ ":serialized:": "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"
56
+ },
57
+ "_last_obs": null,
58
+ "_last_episode_starts": {
59
+ ":type:": "<class 'numpy.ndarray'>",
60
+ ":serialized:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAEBAQEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlC4="
61
+ },
62
+ "_last_original_obs": {
63
+ ":type:": "<class 'collections.OrderedDict'>",
64
+ ":serialized:": "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",
65
+ "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]\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]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]",
66
+ "desired_goal": "[[ 0.1350069 0.05569334 0.08307942]\n [ 0.13247752 0.10502382 0.21178517]\n [-0.1248502 0.0603039 0.13382776]\n [ 0.00119974 0.11899479 0.09277376]\n [-0.01238732 0.10726447 0.0750706 ]\n [-0.00390308 -0.01939992 0.20631182]\n [-0.12361624 0.14267735 0.20663945]\n [ 0.06767705 0.06184439 0.10906996]]",
67
+ "observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00 1.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00 1.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00 1.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00 1.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00 1.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00 1.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00 1.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00 1.0000000e+00]]"
68
+ },
69
+ "_episode_num": 400,
70
+ "use_sde": false,
71
+ "sde_sample_freq": -1,
72
+ "_current_progress_remaining": 0.0,
73
+ "ep_info_buffer": {
74
+ ":type:": "<class 'collections.deque'>",
75
+ ":serialized:": "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"
76
+ },
77
+ "ep_success_buffer": {
78
+ ":type:": "<class 'collections.deque'>",
79
+ ":serialized:": "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"
80
+ },
81
+ "_n_updates": 19000,
82
+ "buffer_size": 1,
83
+ "batch_size": 256,
84
+ "learning_starts": 1000,
85
+ "tau": 0.005,
86
+ "gamma": 0.95,
87
+ "gradient_steps": -1,
88
+ "optimize_memory_usage": false,
89
+ "replay_buffer_class": {
90
+ ":type:": "<class 'abc.ABCMeta'>",
91
+ ":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=",
92
+ "__module__": "stable_baselines3.her.her_replay_buffer",
93
+ "__doc__": "\n Hindsight Experience Replay (HER) buffer.\n Paper: https://arxiv.org/abs/1707.01495\n\n .. warning::\n\n For performance reasons, the maximum number of steps per episodes must be specified.\n In most cases, it will be inferred if you specify ``max_episode_steps`` when registering the environment\n or if you use a ``gym.wrappers.TimeLimit`` (and ``env.spec`` is not None).\n Otherwise, you can directly pass ``max_episode_length`` to the replay buffer constructor.\n\n\n Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n In the online sampling case, these new transitions will not be saved in the replay buffer\n and will only be created at sampling time.\n\n :param env: The training environment\n :param buffer_size: The size of the buffer measured in transitions.\n :param max_episode_length: The maximum length of an episode. If not specified,\n it will be automatically inferred if the environment uses a ``gym.wrappers.TimeLimit`` wrapper.\n :param goal_selection_strategy: Strategy for sampling goals for replay.\n One of ['episode', 'final', 'future']\n :param device: PyTorch device\n :param n_sampled_goal: Number of virtual transitions to create per real transition,\n by sampling new goals.\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ",
94
+ "__init__": "<function HerReplayBuffer.__init__ at 0x7f20c35b5af0>",
95
+ "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7f20c35b5b80>",
96
+ "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7f20c35b5c10>",
97
+ "set_env": "<function HerReplayBuffer.set_env at 0x7f20c35b5ca0>",
98
+ "_get_samples": "<function HerReplayBuffer._get_samples at 0x7f20c35b5d30>",
99
+ "sample": "<function HerReplayBuffer.sample at 0x7f20c35b5dc0>",
100
+ "_sample_offline": "<function HerReplayBuffer._sample_offline at 0x7f20c35b5e50>",
101
+ "sample_goals": "<function HerReplayBuffer.sample_goals at 0x7f20c35b5ee0>",
102
+ "_sample_transitions": "<function HerReplayBuffer._sample_transitions at 0x7f20c35b5f70>",
103
+ "add": "<function HerReplayBuffer.add at 0x7f20c3547040>",
104
+ "store_episode": "<function HerReplayBuffer.store_episode at 0x7f20c35470d0>",
105
+ "_sample_her_transitions": "<function HerReplayBuffer._sample_her_transitions at 0x7f20c3547160>",
106
+ "n_episodes_stored": "<property object at 0x7f20c35452c0>",
107
+ "size": "<function HerReplayBuffer.size at 0x7f20c3547280>",
108
+ "reset": "<function HerReplayBuffer.reset at 0x7f20c3547310>",
109
+ "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7f20c35473a0>",
110
+ "__abstractmethods__": "frozenset()",
111
+ "_abc_impl": "<_abc._abc_data object at 0x7f20c35467c0>"
112
+ },
113
+ "replay_buffer_kwargs": {
114
+ "online_sampling": true,
115
+ "goal_selection_strategy": "future",
116
+ "n_sampled_goal": 4
117
+ },
118
+ "train_freq": {
119
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
120
+ ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
121
+ },
122
+ "use_sde_at_warmup": false,
123
+ "target_entropy": -3.0,
124
+ "ent_coef": "auto",
125
+ "target_update_interval": 1,
126
+ "top_quantiles_to_drop_per_net": 2,
127
+ "batch_norm_stats": [],
128
+ "batch_norm_stats_target": []
129
+ }
tqc-PandaReach-v1/ent_coef_optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ddd8cb557d3e203d0674c579e7eb87b2de139df4b5b019dd2e4a274d29024a6
3
+ size 1507
tqc-PandaReach-v1/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2132b76bb1e30904bffad68a21d6ee732b065a348c9e90a54c1c58f9d2911cc9
3
+ size 83945
tqc-PandaReach-v1/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5306db0cf4e0e402436d8757b79adbca1eb207cc4872a2b908c2f33c8c882777
3
+ size 747
tqc-PandaReach-v1/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
2
+ - Python: 3.9.12
3
+ - Stable-Baselines3: 1.8.0a6
4
+ - PyTorch: 1.13.1+cu117
5
+ - GPU Enabled: True
6
+ - Numpy: 1.24.1
7
+ - Gym: 0.21.0
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43c6fb2ba7d1d3aa6ed8e29713d9a5499ac6b449c60517fc94e5709cf27506ec
3
+ size 10999
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de03886ccdebb7bd644e3041ef5d7e588aefc1a1e9dd217f6f9e71af59ec07fd
3
+ size 5469