Hugging Face's logo

qgallouedec
/
tqc-PandaReach-v1-2786098594

Reinforcement Learning
stable-baselines3
PandaReach-v1
deep-reinforcement-learning
Eval Results
Model card Files Community
1
Quentin Gallouédec commited on
Commit
77aac88
•
1 Parent(s): b15b796

Initial commit

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. README.md +87 -0
  3. args.yml +83 -0
  4. config.yml +30 -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 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: -2.20 +/- 0.75
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_envs', 2),
73
+ ('n_timesteps', 20000.0),
74
+ ('normalize', True),
75
+ ('policy', 'MultiInputPolicy'),
76
+ ('policy_kwargs', 'dict(net_arch=[64, 64], n_critics=1)'),
77
+ ('replay_buffer_class', 'HerReplayBuffer'),
78
+ ('replay_buffer_kwargs',
79
+ "dict( online_sampling=True, goal_selection_strategy='future', "
80
+ 'n_sampled_goal=4 )'),
81
+ ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
82
+ ```
83
+
84
+ # Environment Arguments
85
+ ```python
86
+ {'render': True}
87
+ ```
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
+ - null
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
+ - 2786098594
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - runs/PandaReach-v1__tqc__2786098594__1676295173
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_envs
17
+ - 2
18
+ - - n_timesteps
19
+ - 20000.0
20
+ - - normalize
21
+ - true
22
+ - - policy
23
+ - MultiInputPolicy
24
+ - - policy_kwargs
25
+ - dict(net_arch=[64, 64], n_critics=1)
26
+ - - replay_buffer_class
27
+ - HerReplayBuffer
28
+ - - replay_buffer_kwargs
29
+ - dict( online_sampling=True, goal_selection_strategy='future', n_sampled_goal=4
30
+ )
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 sha256:9aa2d94e10decefe70b4521fd18c777ba6e71599affaf0b710173c80f09130f9
3
+ size 590503
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -2.2, "std_reward": 0.7483314773547882, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T17:01:17.807565"}
tqc-PandaReach-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f529bcf84a08d3efd465993348c1487a076c16df3f6e5608d05f34400af91e64
3
+ size 223981
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:d4f30e4e55faf60097839c2c4defb78ab846f6e3aa55fe3e4c5281c2603dafc8
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 sha256:035559578d90dd75073325b21e93063f3fb0bd4401f47e1f8a8e6fe22523f269
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 0x7fec48363a60>",
8
+ "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7fec48364a80>"
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": 1676295179294746663,
48
+ "learning_rate": {
49
+ ":type:": "<class 'function'>",
50
+ ":serialized:": "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"
51
+ },
52
+ "tensorboard_log": "runs/PandaReach-v1__tqc__2786098594__1676295173/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:": "gAWVdQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYCAAAAAAAAAAEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksChZSMAUOUdJRSlC4="
61
+ },
62
+ "_last_original_obs": {
63
+ ":type:": "<class 'collections.OrderedDict'>",
64
+ ":serialized:": "gAWVYwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolhgAAAAAAAAA6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksCSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolhgAAAAAAAAAzB0CPp4slbx5CzI7HxT0vbIzZz1KB0I+lGgOSwJLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWOAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAAAAAIA/6nIdPRlsGqxDI0o+AAAAAAAAAIAAAAAAAACAP5RoDksCSweGlGgSdJRSlHUu",
65
+ "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]",
66
+ "desired_goal": "[[ 0.12706679 -0.01820975 0.00271675]\n [-0.119179 0.05644578 0.18948093]]",
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]]"
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////9LAHSUYkMIAAAAAAAA8L+UhpRSlIwBbJRLMowBdJRHQHHrM3VCojyMCmlzX3N1Y2Nlc3OUaAloDIwCZjSUiYiHlFKUKEsDaBBOTk5K/////0r/////SwB0lGJDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHHp/BSDRMNoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHIJ8ophF3JoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHIIu0PYnOVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHIplxbSqlxoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHIoYHC4z8BoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHJJX9WIXTFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHJIKVpsXSBoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHJoE7nxJ/ZoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHJm3FUADJVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHKGg0TDfm9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHKFTsyBTXJoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHKmEleF+NNoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHKk3f642CNoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHLEvRqoIfNoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHLDhhDw6QxoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHLjSbUgB91oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHLiE1AJLM9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHMBXi704BFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABDAlIaUUpRoFUsyaBZHQHMAKB/ZuhtoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHMhuh0yP+5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHMghBeHBUJoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHNCNorWiDdoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHNA//rB0p5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHNiGbXpW3loF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHNg5NTLns9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHOCG96C17ZoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHOA5j2Bas9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHOhbfpD/l1oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHOgNxdY4hloF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHPAlBt1p0xoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHO/XlXA/LVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHPgBfnfVI9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHPe0D6nBLxoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHP/VyR0U49oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHP+IOx0MgFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHQelF+d9UloF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHQdX6Q/5cloF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQHQ9SaZx7zFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHQ8E0iyIHloF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHRc8i8nNPhoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHRbvA44p+doF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHR8ZHEuQIVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHR7LWI42jxoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQHSaiRKYiPhoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHSZUoScslNoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHS5X6hxo7FoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHS4KkEcKgJoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHTafb9If8xoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHTZSJwbVBloF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHT6r6P8yetoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHT5eTzND+loF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHUbjWsijcpoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHUaWa6STyJoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHU7Odsi0OVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHU6BB3Roh9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHVcxOtW+49oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHVbjkZJkG1oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHV9VjqfOD9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHV8H2RJVbRoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHWdT0+TvApoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHWcGFWXC0poF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHW8taQmu1ZoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHW7f4ubqhVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHXb9SVGCqZoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQHXav0ulGgBoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAABjAlIaUUpRoFUsyaBZHQHX73VwxWT5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHX6pz90ihZoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHYbn9zfaYhoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHYabfcer+5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHY7tKRMewNoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHY6fmLcbitoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHZcAWBSUC9oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHZaykCV8kVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHZ72A08/2VoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHZ6oHs1KoRoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHabpKaoddVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHaakt29tdloF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHa8D7Q9ic5oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHa62zru6VdoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHbcjwH7gsNoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHbbV94NZvFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHb8x0dRziloF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHb7kFOfukVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHcc+KGcnVpoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHcbwrc0tRNoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHc9118stkFoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHc8oPbwjMVoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHdedsabWmRoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHddQAhje9BoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHd+Z++dsi1oF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHd9MkMTewdoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHefWTxG2CxoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAjAlIaUUpRoFUsyaBZHQHeeJda+vhZoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHe+vuogmqpoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQHe9h3eN1hdoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQHfe0/4ZdfNoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAAAAlIaUUpRoFUsyaBZHQHfdnhS9/SZoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAPC/lIaUUpRoFUsyaBZHQHf+hVuJk5JoF2gJaBpDBAAAgD+UhpRSlHV9lChoBmgJaA9DCAAAAAAAAADAlIaUUpRoFUsyaBZHQHf9TrZ8KHBoF2gJaBpDBAAAgD+UhpRSlHVlLg=="
76
+ },
77
+ "ep_success_buffer": {
78
+ ":type:": "<class 'collections.deque'>",
79
+ ":serialized:": "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"
80
+ },
81
+ "_n_updates": 9500,
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 0x7fec487f6af0>",
95
+ "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7fec487f6b80>",
96
+ "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7fec487f6c10>",
97
+ "set_env": "<function HerReplayBuffer.set_env at 0x7fec487f6ca0>",
98
+ "_get_samples": "<function HerReplayBuffer._get_samples at 0x7fec487f6d30>",
99
+ "sample": "<function HerReplayBuffer.sample at 0x7fec487f6dc0>",
100
+ "_sample_offline": "<function HerReplayBuffer._sample_offline at 0x7fec487f6e50>",
101
+ "sample_goals": "<function HerReplayBuffer.sample_goals at 0x7fec487f6ee0>",
102
+ "_sample_transitions": "<function HerReplayBuffer._sample_transitions at 0x7fec487f6f70>",
103
+ "add": "<function HerReplayBuffer.add at 0x7fec48787040>",
104
+ "store_episode": "<function HerReplayBuffer.store_episode at 0x7fec487870d0>",
105
+ "_sample_her_transitions": "<function HerReplayBuffer._sample_her_transitions at 0x7fec48787160>",
106
+ "n_episodes_stored": "<property object at 0x7fec487853b0>",
107
+ "size": "<function HerReplayBuffer.size at 0x7fec48787280>",
108
+ "reset": "<function HerReplayBuffer.reset at 0x7fec48787310>",
109
+ "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7fec487873a0>",
110
+ "__abstractmethods__": "frozenset()",
111
+ "_abc_impl": "<_abc._abc_data object at 0x7fec48786bc0>"
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 sha256:0a8364fe7e87c9987d45955ebb961ba52ee222db281e352220ab5854727f90c0
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:bffcb780888719fc6be2881f389db79fa052355493f96e90a8e53501cbaa8554
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 sha256:1e30c9ba6163837f635c4e6eeff88c7b037aeaa05dcc4b5d334245a8bd95a435
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 sha256:0dc54c552b6966f83a2345de8c3043606a9e3caed6ee63d134b46d4e43e0d416
3
+ size 9955
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c623045f9f14d6b0c3166222b54d2b09e8269684ce28c7246dd7d3c2b8397a83
3
+ size 5133