Initial commit

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 3003.20 +/- 9.77
+      value: 3000.47 +/- 12.58
       name: mean_reward
     task:
       type: reinforcement-learning

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced883fde344cd5531fe563acb4a678709ce7bce8f249a5bd047790554e5210d
+size 1532937

results.json

@@ -1 +1 @@
-{"mean_reward": 3003.2044213, "std_reward": 9.768151272485037, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-04T22:23:17.491627"}
+{"mean_reward": 3000.4744345, "std_reward": 12.58479606855654, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-04T22:31:11.115167"}

tqc-donkey-mountain-track-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd2a6e624eef5badbe2e856b8b6956455346035aeffe7c8e37015e673dddfc7a
+oid sha256:f5b0aaf55f82f2bfa0a2293ec5e6921414d9e2b2b192af1b27fbe5290aacfde0
 size 3968979

tqc-donkey-mountain-track-v0/data

@@ -4,17 +4,17 @@
         ":serialized:": "gASVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
         "__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 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 features_extractor_kwargs: Keyword arguments\n        to pass to the feature extractor.\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 TQCPolicy.__init__ at 0x7f509167d3b0>",
-        "_build": "<function TQCPolicy._build at 0x7f509167d440>",
-        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f509167d4d0>",
-        "reset_noise": "<function TQCPolicy.reset_noise at 0x7f509167d560>",
-        "make_actor": "<function TQCPolicy.make_actor at 0x7f509167d5f0>",
-        "make_critic": "<function TQCPolicy.make_critic at 0x7f509167d680>",
-        "forward": "<function TQCPolicy.forward at 0x7f509167d710>",
-        "_predict": "<function TQCPolicy._predict at 0x7f509167d7a0>",
-        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f509167d830>",
+        "__init__": "<function TQCPolicy.__init__ at 0x7f50d6d963b0>",
+        "_build": "<function TQCPolicy._build at 0x7f50d6d96440>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f50d6d964d0>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7f50d6d96560>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7f50d6d965f0>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7f50d6d96680>",
+        "forward": "<function TQCPolicy.forward at 0x7f50d6d96710>",
+        "_predict": "<function TQCPolicy._predict at 0x7f50d6d967a0>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f50d6d96830>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f509166a810>"
+        "_abc_impl": "<_abc_data object at 0x7f50d6d83810>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -103,12 +103,12 @@
         ":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
         "__module__": "stable_baselines3.common.buffers",
         "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\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:\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\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 ReplayBuffer.__init__ at 0x7f5091f1c830>",
-        "add": "<function ReplayBuffer.add at 0x7f5091f1c8c0>",
-        "sample": "<function ReplayBuffer.sample at 0x7f5091a88f80>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f5091a87050>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7f50d7636830>",
+        "add": "<function ReplayBuffer.add at 0x7f50d76368c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f50d71a1f80>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f50d71a0050>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f5091f58cc0>"
+        "_abc_impl": "<_abc_data object at 0x7f50d7671cc0>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {