Initial commit

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- PandaPickAndPlace-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: PandaPickAndPlace-v3
+      type: PandaPickAndPlace-v3
+    metrics:
+    - type: mean_reward
+      value: -6.30 +/- 1.79
+      name: mean_reward
+      verified: false
+---
+
+# **TQC** Agent playing **PandaPickAndPlace-v3**
+This is a trained model of a **TQC** agent playing **PandaPickAndPlace-v3**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -0,0 +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 0x7f1b96ae4a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f1b96ada600>"}, "verbose": 0, "policy_kwargs": {"net_arch": [512, 512, 512], "n_critics": 2, "use_sde": false}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1691640582330842520, "learning_rate": 0.0001, "tensorboard_log": "runs/w7lzlwnx", "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVXwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAAjLtMPSBB2L0VwaM8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAA5vQKvsuFOT2Xy0U+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWTAAAAAAAAAC2A4k9cJm7vElCOz5uXcC9G3KUvwsnrb++6489jLtMPSBB2L0VwaM85o2WNlpZAbj8JYK20o7Atm7GNzdse6q2MnVbMw4rhblyy8q4lGgOSwFLE4aUaBJ0lFKUdS4=", "achieved_goal": "[[ 0.04998355 -0.10559297  0.01998953]]", "desired_goal": "[[-0.13569984  0.04529361  0.19315945]]", "observation": "[[ 6.69016093e-02 -2.29003131e-02  1.82870045e-01 -9.39282030e-02\n  -1.15973222e+00 -1.35275400e+00  7.02738613e-02  4.99835461e-02\n  -1.05592966e-01  1.99895296e-02  4.48686751e-06 -3.08392118e-05\n  -3.87872387e-06 -5.73867237e-06  1.09538505e-05 -5.08076300e-06\n   5.10964995e-08 -2.53998151e-04 -9.67000524e-05]]"}, "_episode_num": 68968, "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:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiJiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="}, "_n_updates": 999936, "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": 64, "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 0x7f1b96e16c20>", "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7f1b96e16cb0>", "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7f1b96e16d40>", "set_env": "<function HerReplayBuffer.set_env at 0x7f1b96e16dd0>", "add": "<function HerReplayBuffer.add at 0x7f1b96e16e60>", "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x7f1b96e16ef0>", "sample": "<function HerReplayBuffer.sample at 0x7f1b96e16f80>", "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x7f1b96e17010>", "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x7f1b96e170a0>", "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x7f1b96e17130>", "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7f1b96e171c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f1b96e27580>"}, "replay_buffer_kwargs": {"n_sampled_goal": 4, "goal_selection_strategy": "future"}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "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-6.1.38-x86_64-with-glibc2.37 # 1-NixOS SMP PREEMPT_DYNAMIC Wed Jul  5 17:27:38 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0", "PyTorch": "2.0.1", "GPU Enabled": "True", "Numpy": "1.24.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -6.3, "std_reward": 1.7916472867168918, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-10T00:33:18.700513"}

tqc-PandaPickAndPlace-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8536b5102b8ca8ae22972aafc8147ed5fea99089e65ffa318d72c0824d345cee
+size 24280478

tqc-PandaPickAndPlace-v3/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0

tqc-PandaPickAndPlace-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae40c61df866c10fcc9699798087ca9aa972eb3ec8273cd25e32099c37ed88a1
+size 4349899

tqc-PandaPickAndPlace-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2072ea64c0364300be264d0f07bfe59a7fde9746c4fa9289c2998d455c83089d
+size 8868949

tqc-PandaPickAndPlace-v3/data

@@ -0,0 +1,124 @@
+{
+    "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 0x7f1b96ae4a60>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f1b96ada600>"
+    },
+    "verbose": 0,
+    "policy_kwargs": {
+        "net_arch": [
+            512,
+            512,
+            512
+        ],
+        "n_critics": 2,
+        "use_sde": false
+    },
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1691640582330842520,
+    "learning_rate": 0.0001,
+    "tensorboard_log": "runs/w7lzlwnx",
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "gAWVXwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAAjLtMPSBB2L0VwaM8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAA5vQKvsuFOT2Xy0U+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWTAAAAAAAAAC2A4k9cJm7vElCOz5uXcC9G3KUvwsnrb++6489jLtMPSBB2L0VwaM85o2WNlpZAbj8JYK20o7Atm7GNzdse6q2MnVbMw4rhblyy8q4lGgOSwFLE4aUaBJ0lFKUdS4=",
+        "achieved_goal": "[[ 0.04998355 -0.10559297  0.01998953]]",
+        "desired_goal": "[[-0.13569984  0.04529361  0.19315945]]",
+        "observation": "[[ 6.69016093e-02 -2.29003131e-02  1.82870045e-01 -9.39282030e-02\n  -1.15973222e+00 -1.35275400e+00  7.02738613e-02  4.99835461e-02\n  -1.05592966e-01  1.99895296e-02  4.48686751e-06 -3.08392118e-05\n  -3.87872387e-06 -5.73867237e-06  1.09538505e-05 -5.08076300e-06\n   5.10964995e-08 -2.53998151e-04 -9.67000524e-05]]"
+    },
+    "_episode_num": 68968,
+    "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:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiJiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="
+    },
+    "_n_updates": 999936,
+    "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:": "gAWVawIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAABAQEBlGgIjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKUjA1ib3VuZGVkX2Fib3ZllGgRKJYEAAAAAAAAAAEBAQGUaBVLBIWUaBl0lFKUjAZfc2hhcGWUSwSFlIwDbG93lGgRKJYQAAAAAAAAAAAAgL8AAIC/AACAvwAAgL+UaAtLBIWUaBl0lFKUjARoaWdolGgRKJYQAAAAAAAAAAAAgD8AAIA/AACAPwAAgD+UaAtLBIWUaBl0lFKUjAhsb3dfcmVwcpSMBC0xLjCUjAloaWdoX3JlcHKUjAMxLjCUjApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBBfX2dlbmVyYXRvcl9jdG9ylJOUjAVQQ0c2NJRoMowUX19iaXRfZ2VuZXJhdG9yX2N0b3KUk5SGlFKUfZQojA1iaXRfZ2VuZXJhdG9ylIwFUENHNjSUjAVzdGF0ZZR9lChoPYoR2usHO9v61vrfyQHAEc7R5QCMA2luY5SKEAuzua8zroe9PP2goV5zjlp1jApoYXNfdWludDMylEsAjAh1aW50ZWdlcpRLAHVidWIu",
+        "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": 64,
+    "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 0x7f1b96e16c20>",
+        "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7f1b96e16cb0>",
+        "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7f1b96e16d40>",
+        "set_env": "<function HerReplayBuffer.set_env at 0x7f1b96e16dd0>",
+        "add": "<function HerReplayBuffer.add at 0x7f1b96e16e60>",
+        "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x7f1b96e16ef0>",
+        "sample": "<function HerReplayBuffer.sample at 0x7f1b96e16f80>",
+        "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x7f1b96e17010>",
+        "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x7f1b96e170a0>",
+        "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x7f1b96e17130>",
+        "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7f1b96e171c0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f1b96e27580>"
+    },
+    "replay_buffer_kwargs": {
+        "n_sampled_goal": 4,
+        "goal_selection_strategy": "future"
+    },
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "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": []
+}

tqc-PandaPickAndPlace-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c981182a0eecc2c7100faaceac21b9e10f4a890ce99a0225745fc6a24949100
+size 1507

tqc-PandaPickAndPlace-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba575511e431e290f7ec24849f570aae93adf434c9a7b2ec8d2f80e1bf8c9d78
+size 11041767

tqc-PandaPickAndPlace-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd72c9d2e7049c2b273a9f55e3cefd87d3eec8f24ef9f81aacbaf8687ee00944
+size 747

tqc-PandaPickAndPlace-v3/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.38-x86_64-with-glibc2.37 # 1-NixOS SMP PREEMPT_DYNAMIC Wed Jul  5 17:27:38 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0
+- PyTorch: 2.0.1
+- GPU Enabled: True
+- Numpy: 1.24.2
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.26.2