BanUrsus commited on
Commit
e881a5c
1 Parent(s): 89be2e2

Initial commit

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - PandaPickAndPlace-v3
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: PandaPickAndPlace-v3
16
+ type: PandaPickAndPlace-v3
17
+ metrics:
18
+ - type: mean_reward
19
+ value: -6.90 +/- 1.58
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **TQC** Agent playing **PandaPickAndPlace-v3**
25
+ This is a trained model of a **TQC** agent playing **PandaPickAndPlace-v3**
26
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
27
+
28
+ ## Usage (with Stable-baselines3)
29
+ TODO: Add your code
30
+
31
+
32
+ ```python
33
+ from stable_baselines3 import ...
34
+ from huggingface_sb3 import load_from_hub
35
+
36
+ ...
37
+ ```
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMQAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu", "__module__": "sb3_contrib.tqc.policies", "__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 ", "__init__": "<function MultiInputPolicy.__init__ at 0x7f650db064d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f650daf3b40>"}, "verbose": 1, "policy_kwargs": {"net_arch": [512, 512, 512], "n_critics": 2, "n_quantiles": 25, "use_sde": false}, "num_timesteps": 5000000, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1694190359451961218, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVXwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAANAScPXIJZL2HwaM8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAlG3fvaQmPbpkKK89lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWTAAAAAAAAACYYrQ9DaFkvSpheD2LhIK+GZaFvbIBvL+Pi6M9NAScPXIJZL2HwaM8u31AJjrAV7e6Gx+3Rps7N/BLKq+unDs3Dyy2MeiREjrf9sawlGgOSwFLE4aUaBJ0lFKUdS4=", "achieved_goal": "[[ 0.07617989 -0.05567307 0.01998974]]", "desired_goal": "[[-0.10909572 -0.00072155 0.08552626]]", "observation": "[[ 8.8078678e-02 -5.5817652e-02 6.0639538e-02 -2.5491747e-01\n -6.5227695e-02 -1.4688017e+00 7.9856031e-02 7.6179892e-02\n -5.5673070e-02 1.9989742e-02 6.6783778e-16 -1.2859755e-05\n -9.4835941e-06 1.1182221e-05 -1.5488388e-10 1.1182548e-05\n 5.3019060e-09 5.5911997e-04 -1.4476561e-09]]"}, "_episode_num": 491087, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="}, "_n_updates": 5001516, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (19,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True]", "bounded_above": "[ True True True True]", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "buffer_size": 1000000, "batch_size": 2048, "learning_starts": 100, "tau": 0.05, "gamma": 0.95, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.her.her_replay_buffer", "__doc__": "\n Hindsight Experience Replay (HER) buffer.\n Paper: https://arxiv.org/abs/1707.01495\n\n Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n\n .. note::\n\n Compared to other implementations, the ``future`` goal sampling strategy is inclusive:\n the current transition can be used when re-sampling.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param env: The training environment\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\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 :param n_sampled_goal: Number of virtual transitions to create per real transition,\n by sampling new goals.\n :param goal_selection_strategy: Strategy for sampling goals for replay.\n One of ['episode', 'final', 'future']\n :param copy_info_dict: Whether to copy the info dictionary and pass it to\n ``compute_reward()`` method.\n Please note that the copy may cause a slowdown.\n False by default.\n ", "__init__": "<function HerReplayBuffer.__init__ at 0x7f652303b7f0>", "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7f652303b880>", "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7f652303b910>", "set_env": "<function HerReplayBuffer.set_env at 0x7f652303b9a0>", "add": "<function HerReplayBuffer.add at 0x7f652303ba30>", "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x7f652303bac0>", "sample": "<function HerReplayBuffer.sample at 0x7f652303bb50>", "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x7f652303bbe0>", "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x7f652303bc70>", "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x7f652303bd00>", "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7f652303bd90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f65230527c0>"}, "replay_buffer_kwargs": {"goal_selection_strategy": "future", "n_sampled_goal": 4}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -4.0, "ent_coef": "auto", "target_update_interval": 1, "top_quantiles_to_drop_per_net": 2, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.2.0-32-generic-x86_64-with-glibc2.35 # 32~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Aug 18 10:40:13 UTC 2", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.24.1", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1"}}
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07999489a541c16c5e8f368665562a61b41ee44d66f64b6ef71f95aa1ad14165
3
+ size 1039652
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -6.9, "std_reward": 1.57797338380595, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-10T23:30:11.209849"}
tqc-PandaPickAndPlace-v3.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b55898521787d79f364c0bb8b626cf2a4008134eaf1059ee9398e79e15ef7a6
3
+ size 24280461
tqc-PandaPickAndPlace-v3/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.1.0
tqc-PandaPickAndPlace-v3/actor.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7254293115b86bf53cc30fbe03ea9b73eec3077d3b7acdc78a233319f8018605
3
+ size 4349899
tqc-PandaPickAndPlace-v3/critic.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f2a51a069dd2785b82a5070854af728085cec5c87826d75d9f4f13ca06e76eb
3
+ size 8868949
tqc-PandaPickAndPlace-v3/data ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 0x7f650db064d0>",
8
+ "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7f650daf3b40>"
10
+ },
11
+ "verbose": 1,
12
+ "policy_kwargs": {
13
+ "net_arch": [
14
+ 512,
15
+ 512,
16
+ 512
17
+ ],
18
+ "n_critics": 2,
19
+ "n_quantiles": 25,
20
+ "use_sde": false
21
+ },
22
+ "num_timesteps": 5000000,
23
+ "_total_timesteps": 5000000,
24
+ "_num_timesteps_at_start": 0,
25
+ "seed": null,
26
+ "action_noise": null,
27
+ "start_time": 1694190359451961218,
28
+ "learning_rate": 0.001,
29
+ "tensorboard_log": null,
30
+ "_last_obs": null,
31
+ "_last_episode_starts": {
32
+ ":type:": "<class 'numpy.ndarray'>",
33
+ ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
34
+ },
35
+ "_last_original_obs": {
36
+ ":type:": "<class 'collections.OrderedDict'>",
37
+ ":serialized:": "gAWVXwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAANAScPXIJZL2HwaM8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAlG3fvaQmPbpkKK89lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWTAAAAAAAAACYYrQ9DaFkvSpheD2LhIK+GZaFvbIBvL+Pi6M9NAScPXIJZL2HwaM8u31AJjrAV7e6Gx+3Rps7N/BLKq+unDs3Dyy2MeiREjrf9sawlGgOSwFLE4aUaBJ0lFKUdS4=",
38
+ "achieved_goal": "[[ 0.07617989 -0.05567307 0.01998974]]",
39
+ "desired_goal": "[[-0.10909572 -0.00072155 0.08552626]]",
40
+ "observation": "[[ 8.8078678e-02 -5.5817652e-02 6.0639538e-02 -2.5491747e-01\n -6.5227695e-02 -1.4688017e+00 7.9856031e-02 7.6179892e-02\n -5.5673070e-02 1.9989742e-02 6.6783778e-16 -1.2859755e-05\n -9.4835941e-06 1.1182221e-05 -1.5488388e-10 1.1182548e-05\n 5.3019060e-09 5.5911997e-04 -1.4476561e-09]]"
41
+ },
42
+ "_episode_num": 491087,
43
+ "use_sde": false,
44
+ "sde_sample_freq": -1,
45
+ "_current_progress_remaining": 0.0,
46
+ "_stats_window_size": 100,
47
+ "ep_info_buffer": {
48
+ ":type:": "<class 'collections.deque'>",
49
+ ":serialized:": "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"
50
+ },
51
+ "ep_success_buffer": {
52
+ ":type:": "<class 'collections.deque'>",
53
+ ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="
54
+ },
55
+ "_n_updates": 5001516,
56
+ "observation_space": {
57
+ ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
58
+ ":serialized:": "gAWVMgQAAAAAAACMFWd5bW5hc2l1bS5zcGFjZXMuZGljdJSMBERpY3SUk5QpgZR9lCiMBnNwYWNlc5SMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwUZ3ltbmFzaXVtLnNwYWNlcy5ib3iUjANCb3iUk5QpgZR9lCiMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowNYm91bmRlZF9iZWxvd5SMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYDAAAAAAAAAAEBAZRoE4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksDhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoHCiWAwAAAAAAAAABAQGUaCBLA4WUaCR0lFKUjAZfc2hhcGWUSwOFlIwDbG93lGgcKJYMAAAAAAAAAAAAIMEAACDBAAAgwZRoFksDhZRoJHSUUpSMBGhpZ2iUaBwolgwAAAAAAAAAAAAgQQAAIEEAACBBlGgWSwOFlGgkdJRSlIwIbG93X3JlcHKUjAUtMTAuMJSMCWhpZ2hfcmVwcpSMBDEwLjCUjApfbnBfcmFuZG9tlE51YowMZGVzaXJlZF9nb2FslGgNKYGUfZQoaBBoFmgZaBwolgMAAAAAAAAAAQEBlGggSwOFlGgkdJRSlGgnaBwolgMAAAAAAAAAAQEBlGggSwOFlGgkdJRSlGgsSwOFlGguaBwolgwAAAAAAAAAAAAgwQAAIMEAACDBlGgWSwOFlGgkdJRSlGgzaBwolgwAAAAAAAAAAAAgQQAAIEEAACBBlGgWSwOFlGgkdJRSlGg4jAUtMTAuMJRoOowEMTAuMJRoPE51YowLb2JzZXJ2YXRpb26UaA0pgZR9lChoEGgWaBloHCiWEwAAAAAAAAABAQEBAQEBAQEBAQEBAQEBAQEBlGggSxOFlGgkdJRSlGgnaBwolhMAAAAAAAAAAQEBAQEBAQEBAQEBAQEBAQEBAZRoIEsThZRoJHSUUpRoLEsThZRoLmgcKJZMAAAAAAAAAAAAIMEAACDBAAAgwQAAIMEAACDBAAAgwQAAIMEAACDBAAAgwQAAIMEAACDBAAAgwQAAIMEAACDBAAAgwQAAIMEAACDBAAAgwQAAIMGUaBZLE4WUaCR0lFKUaDNoHCiWTAAAAAAAAAAAACBBAAAgQQAAIEEAACBBAAAgQQAAIEEAACBBAAAgQQAAIEEAACBBAAAgQQAAIEEAACBBAAAgQQAAIEEAACBBAAAgQQAAIEEAACBBlGgWSxOFlGgkdJRSlGg4jAUtMTAuMJRoOowEMTAuMJRoPE51YnVoLE5oEE5oPE51Yi4=",
59
+ "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (19,), float32))])",
60
+ "_shape": null,
61
+ "dtype": null,
62
+ "_np_random": null
63
+ },
64
+ "action_space": {
65
+ ":type:": "<class 'gymnasium.spaces.box.Box'>",
66
+ ":serialized:": "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",
67
+ "dtype": "float32",
68
+ "bounded_below": "[ True True True True]",
69
+ "bounded_above": "[ True True True True]",
70
+ "_shape": [
71
+ 4
72
+ ],
73
+ "low": "[-1. -1. -1. -1.]",
74
+ "high": "[1. 1. 1. 1.]",
75
+ "low_repr": "-1.0",
76
+ "high_repr": "1.0",
77
+ "_np_random": "Generator(PCG64)"
78
+ },
79
+ "n_envs": 1,
80
+ "buffer_size": 1000000,
81
+ "batch_size": 2048,
82
+ "learning_starts": 100,
83
+ "tau": 0.05,
84
+ "gamma": 0.95,
85
+ "gradient_steps": 1,
86
+ "optimize_memory_usage": false,
87
+ "replay_buffer_class": {
88
+ ":type:": "<class 'abc.ABCMeta'>",
89
+ ":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=",
90
+ "__module__": "stable_baselines3.her.her_replay_buffer",
91
+ "__doc__": "\n Hindsight Experience Replay (HER) buffer.\n Paper: https://arxiv.org/abs/1707.01495\n\n Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n\n .. note::\n\n Compared to other implementations, the ``future`` goal sampling strategy is inclusive:\n the current transition can be used when re-sampling.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param env: The training environment\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\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 :param n_sampled_goal: Number of virtual transitions to create per real transition,\n by sampling new goals.\n :param goal_selection_strategy: Strategy for sampling goals for replay.\n One of ['episode', 'final', 'future']\n :param copy_info_dict: Whether to copy the info dictionary and pass it to\n ``compute_reward()`` method.\n Please note that the copy may cause a slowdown.\n False by default.\n ",
92
+ "__init__": "<function HerReplayBuffer.__init__ at 0x7f652303b7f0>",
93
+ "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7f652303b880>",
94
+ "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7f652303b910>",
95
+ "set_env": "<function HerReplayBuffer.set_env at 0x7f652303b9a0>",
96
+ "add": "<function HerReplayBuffer.add at 0x7f652303ba30>",
97
+ "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x7f652303bac0>",
98
+ "sample": "<function HerReplayBuffer.sample at 0x7f652303bb50>",
99
+ "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x7f652303bbe0>",
100
+ "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x7f652303bc70>",
101
+ "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x7f652303bd00>",
102
+ "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7f652303bd90>",
103
+ "__abstractmethods__": "frozenset()",
104
+ "_abc_impl": "<_abc._abc_data object at 0x7f65230527c0>"
105
+ },
106
+ "replay_buffer_kwargs": {
107
+ "goal_selection_strategy": "future",
108
+ "n_sampled_goal": 4
109
+ },
110
+ "train_freq": {
111
+ ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
112
+ ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
113
+ },
114
+ "use_sde_at_warmup": false,
115
+ "target_entropy": -4.0,
116
+ "ent_coef": "auto",
117
+ "target_update_interval": 1,
118
+ "top_quantiles_to_drop_per_net": 2,
119
+ "lr_schedule": {
120
+ ":type:": "<class 'function'>",
121
+ ":serialized:": "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"
122
+ },
123
+ "batch_norm_stats": [],
124
+ "batch_norm_stats_target": []
125
+ }
tqc-PandaPickAndPlace-v3/ent_coef_optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6b384b82787a3ec5324dc26767fdd711a192cb6c562ca06aa015e96e759db83
3
+ size 1507
tqc-PandaPickAndPlace-v3/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:856fd4af1b71a169b4370e3a8ecc8ae0913523549ccf153687d9170e8c815fd2
3
+ size 11041767
tqc-PandaPickAndPlace-v3/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64a18bc001e860d675afa44066b4742f2ef76f5e5b557131058947cdf8cc1ba6
3
+ size 747
tqc-PandaPickAndPlace-v3/system_info.txt ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ - OS: Linux-6.2.0-32-generic-x86_64-with-glibc2.35 # 32~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Aug 18 10:40:13 UTC 2
2
+ - Python: 3.10.12
3
+ - Stable-Baselines3: 2.1.0
4
+ - PyTorch: 2.0.1+cu118
5
+ - GPU Enabled: True
6
+ - Numpy: 1.24.1
7
+ - Cloudpickle: 2.2.1
8
+ - Gymnasium: 0.29.1
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3df90f2fe77ecd5517d93e13a9159fdf4dd3dab6a8863ded0d8e9616c898cc7b
3
+ size 3214