Hugging Face's logo

qgallouedec
/
tqc-PandaPush-v1-696465265

Reinforcement Learning
stable-baselines3
PandaPush-v1
deep-reinforcement-learning
Eval Results
Model card Files Community
1
Quentin Gallouédec commited on
Commit
6dadeef
•
1 Parent(s): 2047004

Initial commit

Browse files
Files changed (17) hide show
  1. .gitattributes +1 -0
  2. README.md +86 -0
  3. args.yml +84 -0
  4. config.yml +28 -0
  5. env_kwargs.yml +1 -0
  6. replay.mp4 +3 -0
  7. results.json +1 -0
  8. tqc-PandaPush-v1.zip +3 -0
  9. tqc-PandaPush-v1/_stable_baselines3_version +1 -0
  10. tqc-PandaPush-v1/actor.optimizer.pth +3 -0
  11. tqc-PandaPush-v1/critic.optimizer.pth +3 -0
  12. tqc-PandaPush-v1/data +130 -0
  13. tqc-PandaPush-v1/ent_coef_optimizer.pth +3 -0
  14. tqc-PandaPush-v1/policy.pth +3 -0
  15. tqc-PandaPush-v1/pytorch_variables.pth +3 -0
  16. tqc-PandaPush-v1/system_info.txt +7 -0
  17. train_eval_metrics.zip +3 -0
.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 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - PandaPush-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: PandaPush-v1
16
+ type: PandaPush-v1
17
+ metrics:
18
+ - type: mean_reward
19
+ value: -6.80 +/- 2.09
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **TQC** Agent playing **PandaPush-v1**
25
+ This is a trained model of a **TQC** agent playing **PandaPush-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 PandaPush-v1 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo tqc --env PandaPush-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 PandaPush-v1 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo tqc --env PandaPush-v1 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo tqc --env PandaPush-v1 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo tqc --env PandaPush-v1 -f logs/ -orga qgallouedec
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('batch_size', 2048),
66
+ ('buffer_size', 1000000),
67
+ ('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
68
+ ('gamma', 0.95),
69
+ ('gradient_steps', -1),
70
+ ('learning_rate', 0.001),
71
+ ('n_envs', 2),
72
+ ('n_timesteps', 1000000.0),
73
+ ('policy', 'MultiInputPolicy'),
74
+ ('policy_kwargs', 'dict(net_arch=[512, 512, 512], n_critics=2)'),
75
+ ('replay_buffer_class', 'HerReplayBuffer'),
76
+ ('replay_buffer_kwargs',
77
+ "dict( online_sampling=True, goal_selection_strategy='future', "
78
+ 'n_sampled_goal=4, )'),
79
+ ('tau', 0.05),
80
+ ('normalize', False)])
81
+ ```
82
+
83
+ # Environment Arguments
84
+ ```python
85
+ {'render': True}
86
+ ```
args.yml ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - tqc
4
+ - - conf_file
5
+ - null
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - PandaPush-v1
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_episodes
13
+ - 20
14
+ - - eval_freq
15
+ - 25000
16
+ - - gym_packages
17
+ - []
18
+ - - hyperparams
19
+ - gradient_steps: -1
20
+ n_envs: 2
21
+ - - log_folder
22
+ - logs
23
+ - - log_interval
24
+ - -1
25
+ - - max_total_trials
26
+ - null
27
+ - - n_eval_envs
28
+ - 5
29
+ - - n_evaluations
30
+ - null
31
+ - - n_jobs
32
+ - 1
33
+ - - n_startup_trials
34
+ - 10
35
+ - - n_timesteps
36
+ - -1
37
+ - - n_trials
38
+ - 500
39
+ - - no_optim_plots
40
+ - false
41
+ - - num_threads
42
+ - -1
43
+ - - optimization_log_path
44
+ - null
45
+ - - optimize_hyperparameters
46
+ - false
47
+ - - progress
48
+ - false
49
+ - - pruner
50
+ - median
51
+ - - sampler
52
+ - tpe
53
+ - - save_freq
54
+ - -1
55
+ - - save_replay_buffer
56
+ - false
57
+ - - seed
58
+ - 696465265
59
+ - - storage
60
+ - null
61
+ - - study_name
62
+ - null
63
+ - - tensorboard_log
64
+ - runs/PandaPush-v1__tqc__696465265__1677338990
65
+ - - track
66
+ - true
67
+ - - trained_agent
68
+ - ''
69
+ - - truncate_last_trajectory
70
+ - true
71
+ - - uuid
72
+ - false
73
+ - - vec_env
74
+ - subproc
75
+ - - verbose
76
+ - 1
77
+ - - wandb_entity
78
+ - qgallouedec
79
+ - - wandb_project_name
80
+ - vec-her-sb3
81
+ - - wandb_tags
82
+ - []
83
+ - - yaml_file
84
+ - null
config.yml ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 2048
4
+ - - buffer_size
5
+ - 1000000
6
+ - - env_wrapper
7
+ - sb3_contrib.common.wrappers.TimeFeatureWrapper
8
+ - - gamma
9
+ - 0.95
10
+ - - gradient_steps
11
+ - -1
12
+ - - learning_rate
13
+ - 0.001
14
+ - - n_envs
15
+ - 2
16
+ - - n_timesteps
17
+ - 1000000.0
18
+ - - policy
19
+ - MultiInputPolicy
20
+ - - policy_kwargs
21
+ - dict(net_arch=[512, 512, 512], n_critics=2)
22
+ - - replay_buffer_class
23
+ - HerReplayBuffer
24
+ - - replay_buffer_kwargs
25
+ - dict( online_sampling=True, goal_selection_strategy='future', n_sampled_goal=4,
26
+ )
27
+ - - tau
28
+ - 0.05
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 sha256:604450e8fc7187fc0bc4998b30f02485953f2215492dcb7ebb4e77deb0b1e3dc
3
+ size 876294
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -6.8, "std_reward": 2.08806130178211, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T13:42:36.352938"}
tqc-PandaPush-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2bd210b423772ec0761e22d2b6f6f3219fc78963adcd2336c03bc86f99b4a59
3
+ size 24264478
tqc-PandaPush-v1/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.8.0a6
tqc-PandaPush-v1/actor.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af6e6b890df3426252e72cca26e6f1afb029a3e325d9f445473d8d10d0b93b1
3
+ size 4341707
tqc-PandaPush-v1/critic.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21309685a6433959f9cda748655873550511c125e9451770f72cc1e271193281
3
+ size 8860757
tqc-PandaPush-v1/data ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 0x7fe5ed5a7c10>",
8
+ "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7fe5ed5aa200>"
10
+ },
11
+ "verbose": 1,
12
+ "policy_kwargs": {
13
+ "net_arch": [
14
+ 512,
15
+ 512,
16
+ 512
17
+ ],
18
+ "n_critics": 2,
19
+ "use_sde": false
20
+ },
21
+ "observation_space": {
22
+ ":type:": "<class 'gym.spaces.dict.Dict'>",
23
+ ":serialized:": "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",
24
+ "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. -10. -10. -10. -10. -10. -10. -10. -10.\n -10. -10. -10. -10. 0.], [10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10.\n 1.], (19,), float32))])",
25
+ "_shape": null,
26
+ "dtype": null,
27
+ "_np_random": null
28
+ },
29
+ "action_space": {
30
+ ":type:": "<class 'gym.spaces.box.Box'>",
31
+ ":serialized:": "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",
32
+ "dtype": "float32",
33
+ "_shape": [
34
+ 3
35
+ ],
36
+ "low": "[-1. -1. -1.]",
37
+ "high": "[1. 1. 1.]",
38
+ "bounded_below": "[ True True True]",
39
+ "bounded_above": "[ True True True]",
40
+ "_np_random": "RandomState(MT19937)"
41
+ },
42
+ "n_envs": 1,
43
+ "num_timesteps": 1000000,
44
+ "_total_timesteps": 1000000,
45
+ "_num_timesteps_at_start": 0,
46
+ "seed": 0,
47
+ "action_noise": null,
48
+ "start_time": 1677339008348619772,
49
+ "learning_rate": {
50
+ ":type:": "<class 'function'>",
51
+ ":serialized:": "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"
52
+ },
53
+ "tensorboard_log": "runs/PandaPush-v1__tqc__696465265__1677338990/PandaPush-v1",
54
+ "lr_schedule": {
55
+ ":type:": "<class 'function'>",
56
+ ":serialized:": "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"
57
+ },
58
+ "_last_obs": null,
59
+ "_last_episode_starts": {
60
+ ":type:": "<class 'numpy.ndarray'>",
61
+ ":serialized:": "gAWVdQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYCAAAAAAAAAAEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksChZSMAUOUdJRSlC4="
62
+ },
63
+ "_last_original_obs": {
64
+ ":type:": "<class 'collections.OrderedDict'>",
65
+ ":serialized:": "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",
66
+ "achieved_goal": "[[-0.08920025 -0.08357045 0.01998946]\n [-0.09874623 -0.02879941 0.01998931]]",
67
+ "desired_goal": "[[-0.08781869 -0.08881433 0.02 ]\n [-0.12314995 -0.01073729 0.02 ]]",
68
+ "observation": "[[-2.15781572e-01 -8.00230532e-02 8.76105980e-03 -4.23450489e-01\n 1.36757391e-01 -1.79806084e-01 -8.92002519e-02 -8.35704464e-02\n 1.99894575e-02 3.62093978e-05 7.66758872e-06 -7.91589333e-03\n -3.39286274e-05 -1.44805712e-05 -6.03468780e-06 3.01589505e-04\n -2.73513639e-06 2.00942703e-04 1.99999996e-02]\n [-3.27978328e-01 -3.45071667e-01 4.19446738e-03 -4.44932361e-01\n -4.39160223e-01 -6.99916947e-03 -9.87462250e-02 -2.87994103e-02\n 1.99893143e-02 4.33735517e-05 7.57072998e-06 1.13703246e-03\n -3.23648525e-05 -8.07234184e-06 -8.35164125e-11 4.32682545e-09\n -1.79615681e-09 1.88818179e-04 1.99999996e-02]]"
69
+ },
70
+ "_episode_num": 20000,
71
+ "use_sde": false,
72
+ "sde_sample_freq": -1,
73
+ "_current_progress_remaining": 0.0,
74
+ "ep_info_buffer": {
75
+ ":type:": "<class 'collections.deque'>",
76
+ ":serialized:": "gAWVLxsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAAAAAAAAIMCUhpRSlIwBbJRLMowBdJRHQNtJiBB/qgSMCmlzX3N1Y2Nlc3OUaAloDIwCZjSUiYiHlFKUKEsDaBBOTk5K/////0r/////SwB0lGJDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABTAlIaUUpRoFUsyaBZHQNtJiKaw2VGMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAHMCUhpRSlGgVSzJoFkdA20pHY8+zMYwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAQwJSGlFKUaBVLMmgWR0DbSkffvWpZjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABjAlIaUUpRoFUsyaBZHQNtLB+YtxuOMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAHMCUhpRSlGgVSzJoFkdA20sIiV0LdIwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAYwJSGlFKUaBVLMmgWR0DbS8hBdD6WjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABDAlIaUUpRoFUsyaBZHQNtLyM+eOGWMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAEMCUhpRSlGgVSzJoFkdA20yG+2E0zowKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAcwJSGlFKUaBVLMmgWR0DbTIeMfigkjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAACbAlIaUUpRoFUsyaBZHQNtNRoRywOiMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAAACUhpRSlGgVSzJoFkdA201HCLMs6YwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAgwJSGlFKUaBVLMmgWR0DbTgmPFNtZjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQNtOChoduHiMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAHMCUhpRSlGgVSzJoFkdA207JRXfZVYwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAcwJSGlFKUaBVLMmgWR0DbTsncrRShjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABjAlIaUUpRoFUsyaBZHQNtPiIMa0hOMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAKsCUhpRSlGgVSzJoFkdA20+JEGqxT4wKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAkwJSGlFKUaBVLMmgWR0DbUEg4hllLjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAACDAlIaUUpRoFUsyaBZHQNtQSM23rliMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAIsCUhpRSlGgVSzJoFkdA21EHe2NNrYwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAYwJSGlFKUaBVLMmgWR0DbUQgG2TgVjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAACbAlIaUUpRoFUsyaBZHQNtRxjVQQ+WMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAHMCUhpRSlGgVSzJoFkdA21HG0HyEtowKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAUwJSGlFKUaBVLMmgWR0DbUoXldTo/jAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABjAlIaUUpRoFUsyaBZHQNtShog/1QKMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAIMCUhpRSlGgVSzJoFkdA21NEGLUCrIwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAQwJSGlFKUaBVLMmgWR0DbU0SqNp/PjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQNtUA3dfsu6MCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAFMCUhpRSlGgVSzJoFkdA21QEFXaJyowKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAcwJSGlFKUaBVLMmgWR0DbVL+7ZnL8jAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABTAlIaUUpRoFUsyaBZHQNtUwEsSTQqMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAFMCUhpRSlGgVSzJoFkdA21V454nndYwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAmwJSGlFKUaBVLMmgWR0DbVXl6qsEJjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABzAlIaUUpRoFUsyaBZHQNtWMX6Eal2MCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAIMCUhpRSlGgVSzJoFkdA21YyIH1OCYwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAYwJSGlFKUaBVLMmgWR0DbVuqHerMljAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQNtW6yon8beMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAGMCUhpRSlGgVSzJoFkdA21ei2ZiNKowKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAgwJSGlFKUaBVLMmgWR0DbV6NmrbQDjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABDAlIaUUpRoFUsyaBZHQNtYWuxKQJaMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAEMCUhpRSlGgVSzJoFkdA21hbc4HX3IwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAIwJSGlFKUaBVLMmgWR0DbWRRCLMs6jAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAACTAlIaUUpRoFUsyaBZHQNtZFOearm2MCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAIMCUhpRSlGgVSzJoFkdA21nMD5j6N4wKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAUwJSGlFKUaBVLMmgWR0DbWcyr7wazjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABTAlIaUUpRoFUsyaBZHQNtahUo4MnaMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAFMCUhpRSlGgVSzJoFkdA21qF9DQZ44wKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAcwJSGlFKUaBVLMmgWR0DbW0COo5xSjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAACLAlIaUUpRoFUsyaBZHQNtbQRje9BeMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAHMCUhpRSlGgVSzJoFkdA21v3LDAJs4wKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAAAJSGlFKUaBVLMmgWR0DbW/e2RaHLjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQNtcryYPXkKMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAEMCUhpRSlGgVSzJoFkdA21yvtxdY4owKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAcwJSGlFKUaBVLMmgWR0DbXWW/0ulHjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABTAlIaUUpRoFUsyaBZHQNtdZlHFxXKMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAHMCUhpRSlGgVSzJoFkdA214d1LrX2IwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAUwJSGlFKUaBVLMmgWR0DbXh5dqtYCjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABTAlIaUUpRoFUsyaBZHQNte1Xjp9qmMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAIsCUhpRSlGgVSzJoFkdA217WBj4Ho4wKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAYwJSGlFKUaBVLMmgWR0DbX4xATqSpjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABjAlIaUUpRoFUsyaBZHQNtfjMfV7QeMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAJsCUhpRSlGgVSzJoFkdA22BDcwQDm4wKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAkwJSGlFKUaBVLMmgWR0DbYEQAlv61jAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABTAlIaUUpRoFUsyaBZHQNtg+0DuBtmMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAFMCUhpRSlGgVSzJoFkdA22D7zRQaaYwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAYwJSGlFKUaBVLMmgWR0DbYbHdsSCfjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABzAlIaUUpRoFUsyaBZHQNthsmkWRA+MCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAALMCUhpRSlGgVSzJoFkdA22JrU83dbowKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAcwJSGlFKUaBVLMmgWR0DbYmvnHNorjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAACDAlIaUUpRoFUsyaBZHQNtjIglByCGMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAHMCUhpRSlGgVSzJoFkdA22Mim/FirowKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAAAJSGlFKUaBVLMmgWR0DbY9i+ZgG9jAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABzAlIaUUpRoFUsyaBZHQNtj2U5dWyWMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAFMCUhpRSlGgVSzJoFkdA22SQ9GI9DIwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAiwJSGlFKUaBVLMmgWR0DbZJF7tzCDjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAACDAlIaUUpRoFUsyaBZHQNtlSIomXw+MCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAHMCUhpRSlGgVSzJoFkdA22VJGz8gp4wKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAUwJSGlFKUaBVLMmgWR0DbZgD3pOerjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAC7AlIaUUpRoFUsyaBZHQNtmAXq3VkOMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAHMCUhpRSlGgVSzJoFkdA22a4QvYe1owKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAgwJSGlFKUaBVLMmgWR0DbZrjdj5KwjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABTAlIaUUpRoFUsyaBZHQNtnb6Wom5WMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAIMCUhpRSlGgVSzJoFkdA22dwHrhR7IwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAYwJSGlFKUaBVLMmgWR0DbaCb7k4m1jAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQNtoJ4y0rsmMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAGMCUhpRSlGgVSzJoFkdA22jeuvUz9IwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAqwJSGlFKUaBVLMmgWR0DbaN9Rm9QGjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQNtplfi5uqGMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAHMCUhpRSlGgVSzJoFkdA22mWi4J/oowKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAQwJSGlFKUaBVLMmgWR0Dbak31SOzZjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABzAlIaUUpRoFUsyaBZHQNtqTnf2saOMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAAACUhpRSlGgVSzJoFkdA22sG4smOVIwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAowJSGlFKUaBVLMmgWR0DbaweIFeOXjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABTAlIaUUpRoFUsyaBZHQNtrvlr2xpuMCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAHMCUhpRSlGgVSzJoFkdA22u+4I8hcYwKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAQwJSGlFKUaBVLMmgWR0DbbHcpWmxdjAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAACDAlIaUUpRoFUsyaBZHQNtsd7PdEb6MCmlzX3N1Y2Nlc3OUaAloGkMEAACAP5SGlFKUdX2UKGgGaAloD0MIAAAAAAAAKMCUhpRSlGgVSzJoFkdA220vzBhx54wKaXNfc3VjY2Vzc5RoCWgaQwQAAIA/lIaUUpR1fZQoaAZoCWgPQwgAAAAAAAAgwJSGlFKUaBVLMmgWR0DbbTBZs9B9jAppc19zdWNjZXNzlGgJaBpDBAAAgD+UhpRSlHVlLg=="
77
+ },
78
+ "ep_success_buffer": {
79
+ ":type:": "<class 'collections.deque'>",
80
+ ":serialized:": "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"
81
+ },
82
+ "_n_updates": 999900,
83
+ "buffer_size": 1,
84
+ "batch_size": 2048,
85
+ "learning_starts": 100,
86
+ "tau": 0.05,
87
+ "gamma": 0.95,
88
+ "gradient_steps": -1,
89
+ "optimize_memory_usage": false,
90
+ "replay_buffer_class": {
91
+ ":type:": "<class 'abc.ABCMeta'>",
92
+ ":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=",
93
+ "__module__": "stable_baselines3.her.her_replay_buffer",
94
+ "__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 ",
95
+ "__init__": "<function HerReplayBuffer.__init__ at 0x7fe5eda38ca0>",
96
+ "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7fe5eda38d30>",
97
+ "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7fe5eda38dc0>",
98
+ "set_env": "<function HerReplayBuffer.set_env at 0x7fe5eda38e50>",
99
+ "_get_samples": "<function HerReplayBuffer._get_samples at 0x7fe5eda38ee0>",
100
+ "sample": "<function HerReplayBuffer.sample at 0x7fe5eda38f70>",
101
+ "_sample_offline": "<function HerReplayBuffer._sample_offline at 0x7fe5ed9cb040>",
102
+ "sample_goals": "<function HerReplayBuffer.sample_goals at 0x7fe5ed9cb0d0>",
103
+ "_sample_transitions": "<function HerReplayBuffer._sample_transitions at 0x7fe5ed9cb160>",
104
+ "add": "<function HerReplayBuffer.add at 0x7fe5ed9cb1f0>",
105
+ "store_episode": "<function HerReplayBuffer.store_episode at 0x7fe5ed9cb280>",
106
+ "_sample_her_transitions": "<function HerReplayBuffer._sample_her_transitions at 0x7fe5ed9cb310>",
107
+ "n_episodes_stored": "<property object at 0x7fe5ed9c83b0>",
108
+ "size": "<function HerReplayBuffer.size at 0x7fe5ed9cb430>",
109
+ "reset": "<function HerReplayBuffer.reset at 0x7fe5ed9cb4c0>",
110
+ "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7fe5ed9cb550>",
111
+ "__abstractmethods__": "frozenset()",
112
+ "_abc_impl": "<_abc._abc_data object at 0x7fe5ed9ca980>"
113
+ },
114
+ "replay_buffer_kwargs": {
115
+ "online_sampling": true,
116
+ "goal_selection_strategy": "future",
117
+ "n_sampled_goal": 4
118
+ },
119
+ "train_freq": {
120
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
121
+ ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
122
+ },
123
+ "use_sde_at_warmup": false,
124
+ "target_entropy": -3.0,
125
+ "ent_coef": "auto",
126
+ "target_update_interval": 1,
127
+ "top_quantiles_to_drop_per_net": 2,
128
+ "batch_norm_stats": [],
129
+ "batch_norm_stats_target": []
130
+ }
tqc-PandaPush-v1/ent_coef_optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b9d13e709a8bf4a1014c42d8c6d0ecb0f3cca2449c901e78cdc90647257e28
3
+ size 1507
tqc-PandaPush-v1/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5bc5600a855d762a126a6e504b31facf999e0ade26c7220c0cf5738c1da9e6
3
+ size 11029479
tqc-PandaPush-v1/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd429df8b4cfd3dc66f5186e440c9bd702d8f073d4548c7043c91c280f5a6cb
3
+ size 747
tqc-PandaPush-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:cce6a0105abb9fb2864f5513d41f43552feff4fa79e94b41d1af8c086be47dd8
3
+ size 532376