araffin commited on
Commit
17e4aea
1 Parent(s): 7465f1f

Initial commit

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - metrics:
12
+ - type: mean_reward
13
+ value: -7.00 +/- 1.79
14
+ name: mean_reward
15
+ task:
16
+ type: reinforcement-learning
17
+ name: reinforcement-learning
18
+ dataset:
19
+ name: PandaPush-v1
20
+ type: PandaPush-v1
21
+ ---
22
+
23
+ # **TQC** Agent playing **PandaPush-v1**
24
+ This is a trained model of a **TQC** agent playing **PandaPush-v1**
25
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
26
+ and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
27
+
28
+ The RL Zoo is a training framework for Stable Baselines3
29
+ reinforcement learning agents,
30
+ with hyperparameter optimization and pre-trained agents included.
31
+
32
+ ## Usage (with SB3 RL Zoo)
33
+
34
+ RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
35
+ SB3: https://github.com/DLR-RM/stable-baselines3<br/>
36
+ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
37
+
38
+ ```
39
+ # Download model and save it into the logs/ folder
40
+ python -m utils.load_from_hub --algo tqc --env PandaPush-v1 -orga sb3 -f logs/
41
+ python enjoy.py --algo tqc --env PandaPush-v1 -f logs/
42
+ ```
43
+
44
+ ## Training (with the RL Zoo)
45
+ ```
46
+ python train.py --algo tqc --env PandaPush-v1 -f logs/
47
+ # Upload the model and generate video (when possible)
48
+ python -m utils.push_to_hub --algo tqc --env PandaPush-v1 -f logs/ -orga sb3
49
+ ```
50
+
51
+ ## Hyperparameters
52
+ ```python
53
+ OrderedDict([('batch_size', 2048),
54
+ ('buffer_size', 1000000),
55
+ ('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
56
+ ('gamma', 0.95),
57
+ ('learning_rate', 0.001),
58
+ ('n_timesteps', 1000000.0),
59
+ ('policy', 'MultiInputPolicy'),
60
+ ('policy_kwargs', 'dict(net_arch=[512, 512, 512], n_critics=2)'),
61
+ ('replay_buffer_class', 'HerReplayBuffer'),
62
+ ('replay_buffer_kwargs',
63
+ "dict( online_sampling=True, goal_selection_strategy='future', "
64
+ 'n_sampled_goal=4, )'),
65
+ ('tau', 0.05),
66
+ ('normalize', False)])
67
+ ```
args.yml ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - tqc
4
+ - - env
5
+ - PandaPush-v1
6
+ - - env_kwargs
7
+ - null
8
+ - - eval_episodes
9
+ - 20
10
+ - - eval_freq
11
+ - 50000
12
+ - - gym_packages
13
+ - []
14
+ - - hyperparams
15
+ - null
16
+ - - log_folder
17
+ - logs
18
+ - - log_interval
19
+ - -1
20
+ - - n_eval_envs
21
+ - 5
22
+ - - n_evaluations
23
+ - 20
24
+ - - n_jobs
25
+ - 1
26
+ - - n_startup_trials
27
+ - 10
28
+ - - n_timesteps
29
+ - -1
30
+ - - n_trials
31
+ - 10
32
+ - - no_optim_plots
33
+ - false
34
+ - - num_threads
35
+ - 2
36
+ - - optimize_hyperparameters
37
+ - false
38
+ - - pruner
39
+ - median
40
+ - - sampler
41
+ - tpe
42
+ - - save_freq
43
+ - -1
44
+ - - save_replay_buffer
45
+ - false
46
+ - - seed
47
+ - 2530685849
48
+ - - storage
49
+ - null
50
+ - - study_name
51
+ - null
52
+ - - tensorboard_log
53
+ - ''
54
+ - - trained_agent
55
+ - ''
56
+ - - truncate_last_trajectory
57
+ - true
58
+ - - uuid
59
+ - false
60
+ - - vec_env
61
+ - dummy
62
+ - - verbose
63
+ - 1
config.yml ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - - learning_rate
11
+ - 0.001
12
+ - - n_timesteps
13
+ - 1000000.0
14
+ - - policy
15
+ - MultiInputPolicy
16
+ - - policy_kwargs
17
+ - dict(net_arch=[512, 512, 512], n_critics=2)
18
+ - - replay_buffer_class
19
+ - HerReplayBuffer
20
+ - - replay_buffer_kwargs
21
+ - dict( online_sampling=True, goal_selection_strategy='future', n_sampled_goal=4,
22
+ )
23
+ - - tau
24
+ - 0.05
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf31ad329db5010ec418b58b021104d62a7de425e10cf1f641d7326d364f5764
3
+ size 801860
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -7.0, "std_reward": 1.7888543819998317, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T21:38:02.365944"}
tqc-PandaPush-v1.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33b9becc733e7b09fb9ba72748d85f41eef841e1be14a37d46aaf84c0b86fab0
3
+ size 24252977
tqc-PandaPush-v1/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.5.1a8
tqc-PandaPush-v1/actor.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0ee351946ca80981a8dc389d518632516777710c38bb147c25855f4191148d
3
+ size 4339049
tqc-PandaPush-v1/critic.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04eaca06c0b3983071410ae11cf527fed91ac8767bfd523c1f25c453f6bd527
3
+ size 8856389
tqc-PandaPush-v1/data ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gASVMQAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 0x7f4275dddcb0>",
8
+ "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc_data object at 0x7f4275e3d6f0>"
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
+ "dtype": null,
26
+ "_np_random": null,
27
+ "_shape": null
28
+ },
29
+ "action_space": {
30
+ ":type:": "<class 'gym.spaces.box.Box'>",
31
+ ":serialized:": "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",
32
+ "dtype": "float32",
33
+ "low": "[-1. -1. -1.]",
34
+ "high": "[1. 1. 1.]",
35
+ "bounded_below": "[ True True True]",
36
+ "bounded_above": "[ True True True]",
37
+ "_np_random": "RandomState(MT19937)",
38
+ "_shape": [
39
+ 3
40
+ ]
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": 1624983752.2027662,
49
+ "learning_rate": {
50
+ ":type:": "<class 'function'>",
51
+ ":serialized:": "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"
52
+ },
53
+ "tensorboard_log": null,
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:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQGUdJRiLg=="
62
+ },
63
+ "_last_original_obs": {
64
+ ":type:": "<class 'collections.OrderedDict'>",
65
+ ":serialized:": "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",
66
+ "achieved_goal": "[[ 0.05858202 -0.11922627 0.0199898 ]]",
67
+ "desired_goal": "[[ 0.06904789 -0.11356129 0.02 ]]",
68
+ "observation": "[[-3.0688959e-01 -1.5922539e-01 1.8300276e-02 -3.9457411e-01\n -2.6129031e-01 -2.8058106e-05 5.8582023e-02 -1.1922627e-01\n 1.9989796e-02 6.7538713e-06 1.9970612e-05 2.6396047e-03\n -6.4572037e-06 4.3866517e-06 9.9711246e-12 5.0880383e-10\n -5.8451605e-10 -1.9524782e-04 2.0000000e-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:": "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"
77
+ },
78
+ "ep_success_buffer": {
79
+ ":type:": "<class 'collections.deque'>",
80
+ ":serialized:": "gASVUwYAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIwVbnVtcHkuY29yZS5tdWx0aWFycmF5lIwGc2NhbGFylJOUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////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/lIaUUpRoB2gNQwQAAAAAlIaUUpRoB2gNQwQAAIA/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/lIaUUpRoB2gNQwQAAAAAlIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAAAAlIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAAAAlIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRoB2gNQwQAAIA/lIaUUpRlLg=="
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:": "gASVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=",
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 0x7f427612f5f0>",
96
+ "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7f427612f680>",
97
+ "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7f427612f710>",
98
+ "set_env": "<function HerReplayBuffer.set_env at 0x7f427612f7a0>",
99
+ "_get_samples": "<function HerReplayBuffer._get_samples at 0x7f427612f830>",
100
+ "sample": "<function HerReplayBuffer.sample at 0x7f427612f8c0>",
101
+ "_sample_offline": "<function HerReplayBuffer._sample_offline at 0x7f427612f950>",
102
+ "sample_goals": "<function HerReplayBuffer.sample_goals at 0x7f427612f9e0>",
103
+ "_sample_transitions": "<function HerReplayBuffer._sample_transitions at 0x7f427612fa70>",
104
+ "add": "<function HerReplayBuffer.add at 0x7f427612fb00>",
105
+ "store_episode": "<function HerReplayBuffer.store_episode at 0x7f427612fb90>",
106
+ "_sample_her_transitions": "<function HerReplayBuffer._sample_her_transitions at 0x7f427612fc20>",
107
+ "n_episodes_stored": "<property object at 0x7f427612e5f0>",
108
+ "size": "<function HerReplayBuffer.size at 0x7f427612fd40>",
109
+ "reset": "<function HerReplayBuffer.reset at 0x7f427612fdd0>",
110
+ "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7f427612fe60>",
111
+ "__abstractmethods__": "frozenset()",
112
+ "_abc_impl": "<_abc_data object at 0x7f427657fe40>"
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:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
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
+ "remove_time_limit_termination": false
129
+ }
tqc-PandaPush-v1/ent_coef_optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d058664e777bb4e21e892578d27774d9ffce92c647566bc8fac3c8ac025bf9be
3
+ size 1255
tqc-PandaPush-v1/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66003eb97bd9ec553d0e8fab5ca4c6f785fc3e4cbd7ad72ec1f754bdfb9b818d
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:f38236a3b972fd506056d06bd0e9a481556dc639c8c142da591855885c0eb0b8
3
+ size 747
tqc-PandaPush-v1/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
2
+ Python: 3.7.10
3
+ Stable-Baselines3: 1.5.1a8
4
+ PyTorch: 1.11.0
5
+ GPU Enabled: True
6
+ Numpy: 1.21.2
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 sha256:64ff3366a8fb243d863ee1b428c5e91d8898e836aaae60ad825184b3e09d5c15
3
+ size 442547