Initial commit

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+library_name: stable-baselines3
+tags:
+- AntBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 3470.79 +/- 34.51
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: AntBulletEnv-v0
+      type: AntBulletEnv-v0
+---
+
+# **TQC** Agent playing **AntBulletEnv-v0**
+This is a trained model of a **TQC** agent playing **AntBulletEnv-v0**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+
+## Usage (with SB3 RL Zoo)
+
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo tqc --env AntBulletEnv-v0 -orga sb3 -f logs/
+python enjoy.py --algo tqc --env AntBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo tqc --env AntBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo tqc --env AntBulletEnv-v0 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('buffer_size', 300000),
+             ('ent_coef', 'auto'),
+             ('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
+             ('gamma', 0.98),
+             ('gradient_steps', 64),
+             ('learning_rate', 0.00073),
+             ('learning_starts', 10000),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=-3, net_arch=[400, 300])'),
+             ('tau', 0.02),
+             ('train_freq', 64),
+             ('use_sde', True),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - env
+    - AntBulletEnv-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - rl-trained-agents/
+  - - log_interval
+    - -1
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 10
+  - - num_threads
+    - -1
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 2054332755
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,29 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - buffer_size
+    - 300000
+  - - ent_coef
+    - auto
+  - - env_wrapper
+    - sb3_contrib.common.wrappers.TimeFeatureWrapper
+  - - gamma
+    - 0.98
+  - - gradient_steps
+    - 64
+  - - learning_rate
+    - 0.00073
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-3, net_arch=[400, 300])
+  - - tau
+    - 0.02
+  - - train_freq
+    - 64
+  - - use_sde
+    - true

env_kwargs.yml

@@ -0,0 +1 @@
+{}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41554def90e17e760d2c7acc80eb4e12d2a088941be149d3f20d06809e43e73a
+size 1267142

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3470.7940238, "std_reward": 34.5072169799714, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T20:53:14.868701"}

tqc-AntBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d813bbeb5fec06a3c99aadcbf5f653cd2896c828fce36b69e11e45c1a4c6fff
+size 6265231

tqc-AntBulletEnv-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a8

tqc-AntBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:599dbb17ab55bbc25501ff210c694720ae7f9ae7e8082db88e62ca515a31167a
+size 1100667

tqc-AntBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b40e045efbd5970e3c9e5817bb0d51dbb85a1d8c0aa3b09c7323d10f64cec8
+size 2294685

tqc-AntBulletEnv-v0/data

@@ -0,0 +1,123 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":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 0x7f71b6f68710>",
+        "_build": "<function TQCPolicy._build at 0x7f71b6f687a0>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f71b6f68830>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7f71b6f688c0>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7f71b6f68950>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7f71b6f689e0>",
+        "forward": "<function TQCPolicy.forward at 0x7f71b6f68a70>",
+        "_predict": "<function TQCPolicy._predict at 0x7f71b6f68b00>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f71b6f68b90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f71b6fc8690>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "log_std_init": -3,
+        "net_arch": [
+            400,
+            300
+        ],
+        "use_sde": true
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n   0.]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf  1.]",
+        "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False  True]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False  True]",
+        "_np_random": null,
+        "_shape": [
+            29
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1. 1. 1.]",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": [
+            8
+        ]
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614621417.2337935,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gASV2QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxVL3ZvbHVtZS9VU0VSU1RPUkUvcmFmZl9hbi9wcm9qZWN0cy90b3JjaHktYmFzZWxpbmVzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS3xDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMVS92b2x1bWUvVVNFUlNUT1JFL3JhZmZfYW4vcHJvamVjdHMvdG9yY2h5LWJhc2VsaW5lcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIH2UfZQoaBdoDowMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBiMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP0frrxAjY7KFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    },
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": null,
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASV/gAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLHYaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUN0x9E7vgV+ub7am24/J1Z3P5EQ3b0h8RG+1x9fvTXdhL4fuMc+LfRqv6Nfgj5dVUG7eOxevxhnsz4vYjU/CSyhPhCfG79N7Bs9qtB+P7KaTb0Ovoa+LmrSvsCosT2tKls+AAAAAAAAgD8AAIA/AAAAAGQ73z2UdJRiLg=="
+    },
+    "_episode_num": 1013,
+    "use_sde": true,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVRAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQKkJvvCMxXaMAWyUTegDjAF0lEdA0VFh1ct5EHV9lChoBkdAqX1IDYAbQ2gHTegDaAhHQNFVn79If8x1fZQoaAZHQKjCjBAv+OxoB03oA2gIR0DRWk44ACGOdX2UKGgGR0CoiMSHmA9WaAdN6ANoCEdA0V624TsY23V9lChoBkdAqOinr6ciGGgHTegDaAhHQNFi4qg/Tsp1fZQoaAZHQKiPgW6bvw5oB03oA2gIR0DRZ07RWtEHdX2UKGgGR0Cowd4OMERraAdN6ANoCEdA0Wuf9ovi+HV9lChoBkdAqZJlrwe/6GgHTegDaAhHQNFwHhvFWGR1fZQoaAZHQKgWki2UjcFoB03oA2gIR0DRdJEtDlYEdX2UKGgGR0CoNOyfcvduaAdN6ANoCEdA0XjbEEkjYHV9lChoBkdAp++4JVsDXGgHTegDaAhHQNGCwNYKYzB1fZQoaAZHQKkONEG7jDNoB03oA2gIR0DRhyQUO/cndX2UKGgGR0CpMOMeOn2qaAdN6ANoCEdA0YtVrpaA4HV9lChoBkdAp/WH5YYBNmgHTegDaAhHQNGPzpn+Q2d1fZQoaAZHQKi4v1bqyGBoB03oA2gIR0DRlAkYm9g4dX2UKGgGR0CoiZUDlo12aAdN6ANoCEdA0ZiPXOnl4nV9lChoBkdAp/VzaGpMpWgHTegDaAhHQNGdCYS6DoR1fZQoaAZHQKc1TsbedkJoB03oA2gIR0DRoT6Dyvs7dX2UKGgGR0Cngio+OfdzaAdN6ANoCEdA0aXC2qkuYnV9lChoBkdAqC03yiEg4mgHTegDaAhHQNGqP2RNh3J1fZQoaAZHQKmXQJaaCtloB03oA2gIR0DRs6ryNGVidX2UKGgGR0Co/Ajin5zpaAdN6ANoCEdA0bgBdO6/ZnV9lChoBkdAqXj9QCSzPmgHTegDaAhHQNG8N+glF+d1fZQoaAZHQKmtzGnXNC9oB03oA2gIR0DRwNdGb1AadX2UKGgGR0CpLw6LOzIFaAdN6ANoCEdA0cVgTrmhd3V9lChoBkdAqQxjAvcrRWgHTegDaAhHQNHJpXUUfxN1fZQoaAZHQKmFPel9BrxoB03oA2gIR0DRzgdF/hESdX2UKGgGR0Cor6LjPv8ZaAdN6ANoCEdA0dKHawD/2nV9lChoBkdAp53BqCYkV2gHTegDaAhHQNHWwAB91EF1fZQoaAZHQHvxSt3fQ8hoB03oA2gIR0DR2yOrYGt7dX2UKGgGR0CpZ0txMnJDaAdN6ANoCEdA0eS/oA4n4XV9lChoBkdAqN2fanJkoWgHTegDaAhHQNHpFvNqxkd1fZQoaAZHQKlK9PBzmwJoB03oA2gIR0DR7a4wpON6dX2UKGgGR0CoiIhIe5nUaAdN6ANoCEdA0fH1yLQ5WHV9lChoBkdAqUQX/1g6VGgHTegDaAhHQNH2etW2gFp1fZQoaAZHQKfHGsySFGpoB03oA2gIR0DR+xJ18stkdX2UKGgGR0CoLgg4ffXPaAdN6ANoCEdA0f+D14Pf9HV9lChoBkdAqXDm+mFajmgHTegDaAhHQNID8YNmUW51fZQoaAZHQKl8uQDmr81oB03oA2gIR0DSCGOOsDGMdX2UKGgGR0CpAJDst03gaAdN6ANoCEdA0gz+HtF8X3V9lChoBkdAqD9NorWiDmgHTegDaAhHQNIWz3mJWNp1fZQoaAZHQKjGzDQZ4wBoB03oA2gIR0DSGwiLCN0edX2UKGgGR0CpGqOiFj/daAdN6ANoCEdA0h982606YHV9lChoBkdAfhYMmF8G92gHTegDaAhHQNIj8yIk7fZ1fZQoaAZHQKiozItDlYFoB03oA2gIR0DSKCp8BuGcdX2UKGgGR0CoolZRKpT/aAdN6ANoCEdA0iytNoakynV9lChoBkdAqJEkJWvKU2gHTegDaAhHQNIw+2hZha11fZQoaAZHQKlFjtw71ZloB03oA2gIR0DSNYI1LrX2dX2UKGgGR0ComGdIGyHEaAdN6ANoCEdA0jn1yO7xu3V9lChoBkdAqNOFn27FsGgHTegDaAhHQNI+OoS6DoR1fZQoaAZHQKi2Hzo2XLNoB03oA2gIR0DSSC0BDG96dX2UKGgGR0CowHQY1pCbaAdN6ANoCEdA0ky2upS75HV9lChoBkdAqBYqHuZ1FGgHTegDaAhHQNJRD1U+9rZ1fZQoaAZHQKlLF+PzWf9oB03oA2gIR0DSVZjc0tROdX2UKGgGR0CoI+VzIV/MaAdN6ANoCEdA0lm8gbIcR3V9lChoBkdAlYx8n3L3bmgHTegDaAhHQNJeTM9wFTx1fZQoaAZHQKjJWu7HyVhoB03oA2gIR0DSYutXCCSSdX2UKGgGR0CozWkmplz2aAdN6ANoCEdA0mdHqpLmIXV9lChoBkdAqLL3jENvwWgHTegDaAhHQNJrxllXiit1fZQoaAZHQKimgr7O3UhoB03oA2gIR0DScHDgGbCrdX2UKGgGR0CpUmZntfG/aAdN6ANoCEdA0npQcSGrS3V9lChoBkdAqH/ayQgcLmgHTegDaAhHQNJ+zd2C/XZ1fZQoaAZHQKi5OF49ovloB03oA2gIR0DSgx1bA1vVdX2UKGgGR0Co8tmPYFq0aAdN6ANoCEdA0oes9Hc1wnV9lChoBkdAqVupOvdM02gHTegDaAhHQNKMJaJ/G2l1fZQoaAZHQKhQjyjpLVZoB03oA2gIR0DSkF88SwnqdX2UKGgGR0CpDdImgJ1JaAdN6ANoCEdA0pSz04R283V9lChoBkdAqG8HerMkhWgHTegDaAhHQNKZKgUQCjl1fZQoaAZHQKigrRpDeCVoB03oA2gIR0DSnWmDoQnQdX2UKGgGR0CoU682itaIaAdN6ANoCEdA0qHKwhGH6HV9lChoBkdAqJFZlUZNwmgHTegDaAhHQNKrTT4UN8V1fZQoaAZHQKfdulDWsiloB03oA2gIR0DSr9qbiIcjdX2UKGgGR0Co8Jh55Z8saAdN6ANoCEdA0rRKMOf/WHV9lChoBkdAqG2g0ZWJamgHTegDaAhHQNK4jnBciW51fZQoaAZHQKhdoUxEfDFoB03oA2gIR0DSvPnB7/n4dX2UKGgGR0Cnjw5k9U0faAdN6ANoCEdA0sFxKBun/HV9lChoBkdAqAtdZeRgZ2gHTegDaAhHQNLFtVUdaMd1fZQoaAZHQKfhVUXpGF1oB03oA2gIR0DSyi8k3S8bdX2UKGgGR0CpCSg62fCiaAdN6ANoCEdA0s5eZf2K23V9lChoBkdAqYk6nNxEOWgHTegDaAhHQNLS0j/dZaF1fZQoaAZHQKm4IeGO+7FoB03oA2gIR0DS3KeCbtqpdX2UKGgGR0CpV5ZG8VYZaAdN6ANoCEdA0uDnA2Q4j3V9lChoBkdAqmuj6FdszmgHTegDaAhHQNLlpbNGEwp1fZQoaAZHQKkmQX9itq5oB03oA2gIR0DS6gK1Bt1qdX2UKGgGR0Ced176pHZsaAdN6ANoCEdA0u4x6hxo7HV9lChoBkdAqgS3ZqVQh2gHTegDaAhHQNLys6JIlMR1fZQoaAZHQKoyEL2HtWxoB03oA2gIR0DS9u5C0F8pdX2UKGgGR0ClMQ3+uNgjaAdN6ANoCEdA0vtnG/N7jXV9lChoBkdAqbvkR6F/QWgHTegDaAhHQNL/2DasZHd1fZQoaAZHQKnm7czImw9oB03oA2gIR0DTBA6f029+dX2UKGgGR0CqCpeb/ffoaAdN6ANoCEdA0w3s+g13uHV9lChoBkdAqb2FyFPBSGgHTegDaAhHQNMSg2R7qpt1fZQoaAZHQKmo1cgQpWpoB03oA2gIR0DTFrTqAz55dX2UKGgGR0Cp+wFMZgogaAdN6ANoCEdA0xtYgMMI/3V9lChoBkdAqlJLebd8A2gHTegDaAhHQNMfj3uZ1FJ1fZQoaAZHQKlePJXhfjVoB03oA2gIR0DTJBlschkidX2UKGgGR0CohWAxJul5aAdN6ANoCEdA0yjEuGbkO3V9lChoBkdAqcKyd4FA3WgHTegDaAhHQNMs/W3rleZ1fZQoaAZHQKlqR91EE1VoB03oA2gIR0DTMYtgqmTDdX2UKGgGR0Cpo2PLHMlkaAdN6ANoCEdA0zYOOP/7znVlLg=="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990016,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.02,
+    "gamma": 0.98,
+    "gradient_steps": 64,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":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 0x7f71b7742b90>",
+        "add": "<function ReplayBuffer.add at 0x7f71b7742c20>",
+        "sample": "<function ReplayBuffer.sample at 0x7f71b72a97a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f71b72a9830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f71b77995d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -8.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "top_quantiles_to_drop_per_net": 2,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
+    },
+    "remove_time_limit_termination": false
+}

tqc-AntBulletEnv-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c84c9646205205a8f54cedec862cd322bb492e02a98807c029b23a63da05bcf0
+size 1255

tqc-AntBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36bdbe95bddbd13919a388195ab1cc5c564f02e22da1415d386f1e20eb4d68dc
+size 2846984

tqc-AntBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:220e52f8fe14c20d16e52d5fe8994f93a219332c118f100e06a33a6b4cabd062
+size 747

tqc-AntBulletEnv-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
+Python: 3.7.10
+Stable-Baselines3: 1.5.1a8
+PyTorch: 1.11.0
+GPU Enabled: True
+Numpy: 1.21.2
+Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da2ca509b79be655465e855fc827b463e11caac9c33039243722073918d988a
+size 48224