Hugging Face's logo

qgallouedec
/
tqc-PandaReach-v1-1760972763

Reinforcement Learning
stable-baselines3
PandaReach-v1
deep-reinforcement-learning
Eval Results
Model card Files Community
4
Quentin Gallouédec commited on
Commit
01e0e56
•
1 Parent(s): ca728dc

Initial commit

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. README.md +86 -0
  3. args.yml +79 -0
  4. config.yml +28 -0
  5. env_kwargs.yml +1 -0
  6. replay.mp4 +3 -0
  7. results.json +1 -0
  8. tqc-PandaReach-v1.zip +3 -0
  9. tqc-PandaReach-v1/_stable_baselines3_version +1 -0
  10. tqc-PandaReach-v1/actor.optimizer.pth +3 -0
  11. tqc-PandaReach-v1/critic.optimizer.pth +3 -0
  12. tqc-PandaReach-v1/data +129 -0
  13. tqc-PandaReach-v1/ent_coef_optimizer.pth +3 -0
  14. tqc-PandaReach-v1/policy.pth +3 -0
  15. tqc-PandaReach-v1/pytorch_variables.pth +3 -0
  16. tqc-PandaReach-v1/system_info.txt +7 -0
  17. train_eval_metrics.zip +3 -0
  18. vec_normalize.pkl +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
+ - 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: -2.10 +/- 0.70
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
+ ('learning_rate', 0.001),
71
+ ('learning_starts', 1000),
72
+ ('n_timesteps', 20000.0),
73
+ ('normalize', True),
74
+ ('policy', 'MultiInputPolicy'),
75
+ ('policy_kwargs', 'dict(net_arch=[64, 64], n_critics=1)'),
76
+ ('replay_buffer_class', 'HerReplayBuffer'),
77
+ ('replay_buffer_kwargs',
78
+ "dict( online_sampling=True, goal_selection_strategy='future', "
79
+ 'n_sampled_goal=4 )'),
80
+ ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
81
+ ```
82
+
83
+ # Environment Arguments
84
+ ```python
85
+ {'render': True}
86
+ ```
args.yml ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - tqc
4
+ - - device
5
+ - auto
6
+ - - env
7
+ - PandaReach-v1
8
+ - - env_kwargs
9
+ - null
10
+ - - eval_episodes
11
+ - 20
12
+ - - eval_freq
13
+ - 25000
14
+ - - gym_packages
15
+ - []
16
+ - - hyperparams
17
+ - null
18
+ - - log_folder
19
+ - logs
20
+ - - log_interval
21
+ - -1
22
+ - - max_total_trials
23
+ - null
24
+ - - n_eval_envs
25
+ - 5
26
+ - - n_evaluations
27
+ - null
28
+ - - n_jobs
29
+ - 1
30
+ - - n_startup_trials
31
+ - 10
32
+ - - n_timesteps
33
+ - -1
34
+ - - n_trials
35
+ - 500
36
+ - - no_optim_plots
37
+ - false
38
+ - - num_threads
39
+ - -1
40
+ - - optimization_log_path
41
+ - null
42
+ - - optimize_hyperparameters
43
+ - false
44
+ - - progress
45
+ - false
46
+ - - pruner
47
+ - median
48
+ - - sampler
49
+ - tpe
50
+ - - save_freq
51
+ - -1
52
+ - - save_replay_buffer
53
+ - false
54
+ - - seed
55
+ - 1760972763
56
+ - - storage
57
+ - null
58
+ - - study_name
59
+ - null
60
+ - - tensorboard_log
61
+ - runs/PandaReach-v1__tqc__1760972763__1670944772
62
+ - - track
63
+ - true
64
+ - - trained_agent
65
+ - ''
66
+ - - truncate_last_trajectory
67
+ - true
68
+ - - uuid
69
+ - false
70
+ - - vec_env
71
+ - dummy
72
+ - - verbose
73
+ - 1
74
+ - - wandb_entity
75
+ - openrlbenchmark
76
+ - - wandb_project_name
77
+ - sb3
78
+ - - yaml_file
79
+ - null
config.yml ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - - learning_rate
13
+ - 0.001
14
+ - - learning_starts
15
+ - 1000
16
+ - - n_timesteps
17
+ - 20000.0
18
+ - - normalize
19
+ - true
20
+ - - policy
21
+ - MultiInputPolicy
22
+ - - policy_kwargs
23
+ - dict(net_arch=[64, 64], n_critics=1)
24
+ - - replay_buffer_class
25
+ - HerReplayBuffer
26
+ - - replay_buffer_kwargs
27
+ - dict( online_sampling=True, goal_selection_strategy='future', n_sampled_goal=4
28
+ )
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 sha256:6d80f4b04d4ca62b562846b1a84fc10c3c61c74b9ebc03d27e65b19d23180065
3
+ size 598365
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -2.1, "std_reward": 0.7, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T16:32:05.443960"}
tqc-PandaReach-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb4bbe582b5a99d0342584257aaf424fa4a1292df51d32fe1daec36bc497d0b6
3
+ size 223881
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:c82af9ab5dc2ad7282ad198c159af80cef56464bd17e417723fd2aa8361f1ccb
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:f681472e4e25241735b89bd6592536ade9c7e4757218035f8936f04595bf374d
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 0x7f0c3ad64a60>",
8
+ "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7f0c3ad62f80>"
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:": "gAWVGAwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLA4WUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWDAAAAAAAAAAAAIC/AACAvwAAgL+UaApLA4WUjAFDlHSUUpSMBGhpZ2iUaBIolgwAAAAAAAAAAACAPwAAgD8AAIA/lGgKSwOFlGgVdJRSlIwNYm91bmRlZF9iZWxvd5RoEiiWAwAAAAAAAAABAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLA4WUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYDAAAAAAAAAAEBAZRoIUsDhZRoFXSUUpSMCl9ucF9yYW5kb22UjBRudW1weS5yYW5kb20uX3BpY2tsZZSMEl9fcmFuZG9tc3RhdGVfY3RvcpSTlIwHTVQxOTkzN5RoLYwUX19iaXRfZ2VuZXJhdG9yX2N0b3KUk5SGlFKUfZQojA1iaXRfZ2VuZXJhdG9ylIwHTVQxOTkzN5SMBXN0YXRllH2UKIwDa2V5lGgSKJbACQAAAAAAAAAAAIBTwrOchwO1k3Lsq1vo5rLyz7aB2tUG72GhMU2ga7XM2RPmGJ90nHkvyKUbgMR5AUmeD0PkXeAYk5ITVczUSilk0giVvjTQnkRyegPwrb8Kc5t7PulgsQbadQNFC2591hZq6wQ0ZoO38/WlL2nvQmNDtVz3wndSzEZENy0IiW7Qjq53+xi2gE97nvlPMuwS2LmOXoWpGcquPXYtZytCgJ7F7scf9SIBXUvPJA/MGVJkRFeYcJ0K9RIXtela3jvE/0HPOrFftofdM9hYiaqizX97P8mUt2wPQx8xmX0bYJCrtwcdGUzeyPuOugD1z6ka3iX+IAalFvzQduPBTvXKQ9MBWnnfUFetzaqYhTrP0WHhMA/Ht9nWRUX4vUiuWi77gKSTLtizn2cHsqRyJMj43mOVvrbJtm3T5laAgDosou93H+ZNC0HiTVqmVP8Lsv3/JsoIWfaq43/tiUiTGgfVTTF1psbquA6tH5Icya9TC+0oH7X0htvTuZKBVDKM0C+fIAM8l/emTHKVm2ft/85WlYRpZ+XoFwvDLSCusSBQr4f7w/xdYy4GCKdeDDOfezLj5k6WvjminpO26pfQqfP9LJIYOUEgrwmoo5vMHp8a36i8kcQzwqUvi94rCQuS64xYFp7HcUF1aySvLmqGyXEyCeTa2GHwNpeYB9u4jyPRKocxbWSV4hOL16R9fH95KLmFfUaMD8zrZmLG5rLUfzMf1WOxNFwZpzInS+HWE1F4MWg2xcVst8upoi9ssNCNjtPbz1ley6m8DG7YZVNupay35yQ8/PAfu8uKRQsL7B4ArDFquqb66ABeDLPvviZ4c6y9Bi67Xye+uu6eNlYO/Boq5iiETBR9Kemi0T1eFf33JRNzywY9CJ1N9eTOb+3wxY/yK3iXhVISAMufwZby3YMCHwTAVr8o4ahkQaNipnYgwDvQT4XYuqBpmVAsUw41MjHfK43kXZ7UxPi/bB0FEr1H6UYynEiI2V3I7DDEsMFNEMyF3sA+J2YPBAGe9oh5woVr3lu3AeREERRPmD778jQMODrzkRfg4w7Zi1M+ozc9CW5Lim4SEBBFW6Q0ZKHiBgOBwE8pmXhOE1/4b4TsSX1+ZYlw/f1KJ/Doyf4YSKwzVGEdjTldkdS/lbivyQPaNIsxj4ggvb4u1CtbuK3vLbz6wSJwugR9g6TL1kkXqXR9H6xcRrB/5EQf0u+1EnjLN/GvsqKw2mvVrG/Vp7kINdL5dPO44b8Emce+3xqudjVdYf1J2QI56iTowjwYEK2NMLEnklukjknSLQDrqYlpFb0sx8/oKKXf9xVFD243YpO1XejusnBjhcKePsMmaqtTCh8MOXsSTQ+g3vDQeHxgc7LyqE/DtXwAt2Nmft5i2MJAiV1C8dszUjvdG0ItC9AYUxdQInTbakZGpO9lfldZKLOpuBfpMmYjosMX3Bylh5qUHtwPB6V+p2nMdGbKNFshf1v7Di6P/9oNGA/ZKCI4Cr8P/3/RJuAr8TQVDJyWE1UCRsrBeEDEoZzOm8mjDSYUVQC3/l9PkoCyZBMC3ynQWysYwNN+ThHNmCplKb6KFVFLfvVPHe3CkYDWCij8Ah8mHyyUkLeGRHU4YI3ssA8YLBsz2seUpJTi66EmJ9/X3qH2rWQ8yV3r3z0x8otWS8KXuh8JG6s9Rbjpx4koT3nWxAPW/xwrQcrUma4FMJcB6UJQIgU0saTe0xc1Wa64UXejfFvhXhPUgBgh8F3IRUeEghk4T8kRjv11pDDyeNgS1DpjBnqQ0IFh+uOrY6CUhNxF3AOYg0vjaujoedtaAtlDwJ78SI9UG1YfCG8ZQcrUU043NHNeBPXMoSD5YCKB64rhBUjF0hMzhi9TJi+lAm4l37EYPWejsFggpd1XhoOWxGdZIyZL7NPJO8LT5OAEwI2ky90KGNoH9dOsxWybS+A+YJizCfTrsxNhZ+bmgKqqY1yKqhF8UvY7abEVPVUxwoOvEcF0FSFIblSYB6vHzooATK1uwJufo46PxjTZXBXKfNd3RYl8uKh4YxkhIzV6d5Z9NzWZDoKl0PEmpSZTzr8qwEvcFvRLY0CoXKwUlkrEPAt6PzHP7EfwjEQfOWSKI0f7YgirTrrcUDCLrCDp2ByvIOpD6U0PCfz3yfKWtxhKGKAOu2sUE17MrHdmOmQ8Kc9R5AHiElStgJQnLkLLK0L/HVSwHIp7P9pI0RaeVafNh0l/Y+govRh+ZpHcqlfOL1rHcEc+CTVx2aB1WSp68UnQNR1MEVCP+aFoqpxpPSsokuDL/XUCFZbidfv6QB2BHRvWICx4jRNswO2iEG6qpRl+ox9Qqx0jy/Zp5R3T4io6M8EV7tNlELs5RiZ/vz1JFOnD2Cy3i3PHu0tqnwmcW3aR4qGp3e8GCqm+WzG/HQNw8L5uj+oiV0qICfkPtM+N5YvMnWCamTWZUo7JY6/9nOVFN97zISwyxFyB0/Fs67EuOU7CjW4WH02Meg7P/FucjrYjj1nNPn0ZQI20AvvhSqOVGjJdnkQsSOFOf4Xl9h8SRjZOdKyAo7hbBv/EPjVLiYEvstxTIXvrJtXtjHQvpXZAahJ/KEcWoxAmz+Fos89bXyZYlv9QOX3Rk31MTNx1e9myYJ6rMJqALpgMend+in7mcBBKdP8HK3aPvP7pyeX9pmHqgqznGsQya7OksVtc1Wh/2E2ZfkTQNDYzy4Gqp5b3mnrPzJKc7FREA7byhhaxtXJ5ho2VYtms60gxkNGONt5xJLAwuWsGHDiZlWG3gOA5DEjX4/uw8dksx/z1T7ly1/WsPSvUBeDJePM7Eq8LFYyGvPoCHX37NqX9sAinD7RXs+rzk9FA7hR5JyYzA4NHyNw58gu4yajvFeF6Zj8mq06dySURoZqkx4aWSJ5+9CTH0vkRa8ufqy0jjNE/illfH2I7PXsgomYo5UeAIgA6KF5vRvCSM2Qi2V9g7cvN4ss+4EM0sWDu1C7k09bLbxricGwT+CzIS15G8XYQJgUg4mDTp3NzvshbDuj7PVDkA/EuD26/IWeJhY24nKTut+UsKZhyDWA3rnsJZ9/xh8+vS6Qo5qZyj3hfWcV3KujEeJCVFdo/3UM6oy54jWkJqzJFC3SO1tbDF0RXLM/cbNRlcFaprTFcLPB7b1zGDZqLAq64ABV9oIT8+3VwlerzC+WIXzWwwM8xujB3367Ja4TGr977ZbfBZ5XeFWh+iITJKMGsk9ZUlb375ShwlsLSmk3Dma0eS2RmpSTqRW1SBVDgKPi52P9uW5nNypaMi84Ik7nYz7FxBjzTwSLxP+XDBL1OC67NDd7QpHuGm2A1xfX9eEK8C5RoB4wCdTSUiYiHlFKUKEsDaAtOTk5K/////0r/////SwB0lGJNcAKFlGgVdJRSlIwDcG9zlE1wAnWMCWhhc19nYXVzc5RLAIwFZ2F1c3OURwAAAAAAAAAAdWJ1Yi4=",
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": 1670944775309363462,
48
+ "learning_rate": {
49
+ ":type:": "<class 'function'>",
50
+ ":serialized:": "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"
51
+ },
52
+ "tensorboard_log": "runs/PandaReach-v1__tqc__1760972763__1670944772/PandaReach-v1",
53
+ "lr_schedule": {
54
+ ":type:": "<class 'function'>",
55
+ ":serialized:": "gAWV/QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZS9ob21lL3FnYWxsb3VlZGVjL3JsLWJhc2VsaW5lczMtem9vL2Vudi9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxlL2hvbWUvcWdhbGxvdWVkZWMvcmwtYmFzZWxpbmVzMy16b28vZW52L2xpYi9weXRob24zLjkvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP1BiTdLxqfyFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
56
+ },
57
+ "_last_obs": null,
58
+ "_last_episode_starts": {
59
+ ":type:": "<class 'numpy.ndarray'>",
60
+ ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
61
+ },
62
+ "_last_original_obs": {
63
+ ":type:": "<class 'collections.OrderedDict'>",
64
+ ":serialized:": "gAWVLwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAA6l56vWihBL7zSTE+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWHAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAAAAAIA/lGgOSwFLB4aUaBJ0lFKUdS4=",
65
+ "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]",
66
+ "desired_goal": "[[-0.06112567 -0.12952197 0.17313366]]",
67
+ "observation": "[[ 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:": "gAWV7hYAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAAAAAAAAAMCUhpRSlIwBbJRLMowBdJRHQGFd+xGDtgOMCmlzX3N1Y2Nlc3OUaAloDIwCZjSUiYiHlFKUKEsDaBBOTk5K/////0r/////SwB0lGJDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGFtNU4rBj5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGF8mVZ9uxdoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABDAlIaUUpRoFUsyaBZHQGGMWitaIN5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGGcm4Ajps5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGGs5zPrv9doF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGG9WlMyrPtoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGHNtw71ZkloF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGHeSc0+C9RoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGHujRc/t6ZoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGH+lbVz6rNoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGIOTnied09oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGIedgfEGaBoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGIuW+fywwFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGI/gJswco9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGJPPhIe5nVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQGJfCMglnh9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGJuLe67NB5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQGJ9oMKCxu9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGKM2e6I3zdoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGKcYFiay8loF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGKrjSw4bS9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGK7H6/IsAhoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGLKW74BV+9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGLZ9cbBGhFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGLqdb5dnkFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGL6PzFuNxVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQGMJwqZtvXNoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGMaSzollbxoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGMp/+KjzqdoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGM6siB5HExoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGNL1Da4+bFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGNcPnKW9lFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGNs4xL0z0poF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGN9T9KmKqJoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGONpB5X2dxoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGOeBsyi22JoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGOuVdHDrJNoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGO+olUp/gBoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGPOq+zt1IRoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGPeqPXCj1xoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGPugxSHdoFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGP+hun/DLtoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGQOb0voNd9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGQfUY8+zMRoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGQvNGmUGFBoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGQ/KVII4VBoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGRRRZdOZb9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGRg052hZhdoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGRwBzV+Zw5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQGR/TdLxqfxoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGSOg8B+4LFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQGSeDp1RtP5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGSt4GUwBYFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGS9wH7gsK9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGTNqpcX3xpoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGTdiJfpljFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGTtNqQA+6loF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGT9OOS4e91oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGUNLrPdEb5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGUdXC9AX2xoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQGUt9VFQVKxoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGU+cYAKfFtoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGVOuAI6bONoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGVfQswtapxoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGVvxTS9du5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGWAYRVZLZloF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGWQxvegte5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGWg5A6dUbVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGWw0TDfm9xoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGXAxJmNBGBoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGXQHNxEORVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGXfgu7HyVhoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQGXvBiCrcTJoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGX+Yo7V8TloF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGYOAZjx0+1oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGYdgNoakyloF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGYs029+PR1oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGY8JDE3sHBoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGZLhvBJqZdoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGZbBHCoCMhoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGZqaSDAaehoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGZ55zxPO6doF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGaJ7ALy+YdoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGaZ9ZJTVDtoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGaqLehwl0JoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGa6uVHFxXJoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGbK5yuIRAdoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGbbVAAyVOdoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGbszwtrbg1oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGb9R6nivPloF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGcNt1yNn5BoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGceDriVB2RoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGcujvmYBvJoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGc/Ackt29toF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQGdPhbOeJ55oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGdfl5nlGPRoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGdvTAnDziFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQGd+6sySFGpoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQGeOdlmOEM9oF2gJaBpDBAAAgD+UhpRSlHVlLg=="
76
+ },
77
+ "ep_success_buffer": {
78
+ ":type:": "<class 'collections.deque'>",
79
+ ":serialized:": "gAWVUwYAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIwVbnVtcHkuY29yZS5tdWx0aWFycmF5lIwGc2NhbGFylJOUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRlLg=="
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 0x7f0c3b1f7af0>",
95
+ "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7f0c3b1f7b80>",
96
+ "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7f0c3b1f7c10>",
97
+ "set_env": "<function HerReplayBuffer.set_env at 0x7f0c3b1f7ca0>",
98
+ "_get_samples": "<function HerReplayBuffer._get_samples at 0x7f0c3b1f7d30>",
99
+ "sample": "<function HerReplayBuffer.sample at 0x7f0c3b1f7dc0>",
100
+ "_sample_offline": "<function HerReplayBuffer._sample_offline at 0x7f0c3b1f7e50>",
101
+ "sample_goals": "<function HerReplayBuffer.sample_goals at 0x7f0c3b1f7ee0>",
102
+ "_sample_transitions": "<function HerReplayBuffer._sample_transitions at 0x7f0c3b1f7f70>",
103
+ "add": "<function HerReplayBuffer.add at 0x7f0c3b187040>",
104
+ "store_episode": "<function HerReplayBuffer.store_episode at 0x7f0c3b1870d0>",
105
+ "_sample_her_transitions": "<function HerReplayBuffer._sample_her_transitions at 0x7f0c3b187160>",
106
+ "n_episodes_stored": "<property object at 0x7f0c3b1847c0>",
107
+ "size": "<function HerReplayBuffer.size at 0x7f0c3b187280>",
108
+ "reset": "<function HerReplayBuffer.reset at 0x7f0c3b187310>",
109
+ "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7f0c3b1873a0>",
110
+ "__abstractmethods__": "frozenset()",
111
+ "_abc_impl": "<_abc._abc_data object at 0x7f0c3b1891c0>"
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 sha256:1c23c11fc5a7e45a86fac7c2c8a239c6bf123014983f16c19bfb2785f71dec25
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:d18e8d33c03ee0a4fab5d8dc87d88ebb25ea279e51595e9037676ae39abb0aef
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 sha256:0c7e38b8d306cea8697c904217dd58a0d80de4a4425e4592dc1cf3f40ebbd042
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:b2df514f03bd8f9f9b3536c3235a087f069d0c01e2136e14be7d549991225624
3
+ size 9563
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0101fe469208523b1378220cb0ca3f4beaa96e96635a6942291fea7f3cabbbe
3
+ size 5077