Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaPickAndPlace-v3
     metrics:
     - type: mean_reward
-      value: -6.30 +/- 2.10
+      value: -5.50 +/- 1.28
       name: mean_reward
       verified: false
 ---

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8495d33c87ec2a2c4b616a8132f00ac68e14cf19729618fdaba0a7b1c17642a
-size 1032629
+oid sha256:f8d717f47f8ceecf2c9d6fdb38247f34410aa96b765fc5c148217422efa84ff6
+size 1048872

results.json

@@ -1 +1 @@
-{"mean_reward": -6.3, "std_reward": 2.1, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-05T14:40:49.477347"}
+{"mean_reward": -5.5, "std_reward": 1.284523257866513, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-05T15:03:34.410948"}

tqc-PandaPickAndPlace-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fe1ddf3620e20ff1fd502f9659c9b30fd4e4640f2d9f3b5cad098b36407e16c
+oid sha256:31f38984df4bc8e62068eee3686adb0348069df1a807687f1750ec81351aaa65
 size 24281849

tqc-PandaPickAndPlace-v3/data

@@ -4,9 +4,9 @@
         ":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 0x7f249d1cf880>",
+        "__init__": "<function MultiInputPolicy.__init__ at 0x7f82cf477880>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f249d1e9980>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f82cf490b00>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -91,19 +91,19 @@
         ":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 0x7f249d741fc0>",
-        "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7f249d742050>",
-        "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7f249d7420e0>",
-        "set_env": "<function HerReplayBuffer.set_env at 0x7f249d742170>",
-        "add": "<function HerReplayBuffer.add at 0x7f249d742200>",
-        "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x7f249d742290>",
-        "sample": "<function HerReplayBuffer.sample at 0x7f249d742320>",
-        "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x7f249d7423b0>",
-        "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x7f249d742440>",
-        "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x7f249d7424d0>",
-        "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7f249d742560>",
+        "__init__": "<function HerReplayBuffer.__init__ at 0x7f82cf7f5fc0>",
+        "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7f82cf7f6050>",
+        "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7f82cf7f60e0>",
+        "set_env": "<function HerReplayBuffer.set_env at 0x7f82cf7f6170>",
+        "add": "<function HerReplayBuffer.add at 0x7f82cf7f6200>",
+        "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x7f82cf7f6290>",
+        "sample": "<function HerReplayBuffer.sample at 0x7f82cf7f6320>",
+        "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x7f82cf7f63b0>",
+        "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x7f82cf7f6440>",
+        "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x7f82cf7f64d0>",
+        "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7f82cf7f6560>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f249d747fc0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f82cf7faa00>"
     },
     "replay_buffer_kwargs": {
         "goal_selection_strategy": "future",