Initial commit

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d976ba1faada64b15dfcddb46fce184836a329c65a5b4af5ec80f33448ba59
+size 220552

results.json

@@ -1 +1 @@
-{"mean_reward": 5.5155896, "std_reward": 1.9174329601274307, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-08T16:52:52.414525"}
+{"mean_reward": 5.5155896, "std_reward": 1.9174329601274307, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-08T16:56:24.632879"}

tqc-LiftCube-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcdbb14f76c9664bbf1b5514651b6a4d87686303396bb9a835ef6ea6bb8b8ae1
+oid sha256:cd7d75ef412e0da5b4112eb41cbd734a985b108c356d0cd4e273e2168b50db1c
 size 3419898

tqc-LiftCube-v0/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 0x7fdd147db370>",
+        "__init__": "<function MultiInputPolicy.__init__ at 0x7f1d96d0f370>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fdd147eef00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f1d96d1f100>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -83,12 +83,12 @@
         "__module__": "stable_baselines3.common.buffers",
         "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray], 'next_observations': typing.Dict[str, numpy.ndarray]}",
         "__doc__": "\n    Dict Replay buffer used in off-policy algorithms like SAC/TD3.\n    Extends the ReplayBuffer to use dictionary observations\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 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    ",
-        "__init__": "<function DictReplayBuffer.__init__ at 0x7fdd15195f30>",
-        "add": "<function DictReplayBuffer.add at 0x7fdd15195fc0>",
-        "sample": "<function DictReplayBuffer.sample at 0x7fdd15196050>",
-        "_get_samples": "<function DictReplayBuffer._get_samples at 0x7fdd151960e0>",
+        "__init__": "<function DictReplayBuffer.__init__ at 0x7f1d976cdf30>",
+        "add": "<function DictReplayBuffer.add at 0x7f1d976cdfc0>",
+        "sample": "<function DictReplayBuffer.sample at 0x7f1d976ce050>",
+        "_get_samples": "<function DictReplayBuffer._get_samples at 0x7f1d976ce0e0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fdd153933c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f1d976bb900>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {