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:
+- MountainCarContinuous-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 94.57 +/- 0.45
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCarContinuous-v0
+      type: MountainCarContinuous-v0
+---
+
+# **PPO** Agent playing **MountainCarContinuous-v0**
+This is a trained model of a **PPO** agent playing **MountainCarContinuous-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
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo ppo --env MountainCarContinuous-v0 -orga sb3 -f logs/
+python enjoy --algo ppo --env MountainCarContinuous-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo ppo --env MountainCarContinuous-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo ppo --env MountainCarContinuous-v0 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('clip_range', 0.1),
+             ('ent_coef', 0.00429),
+             ('gae_lambda', 0.9),
+             ('gamma', 0.9999),
+             ('learning_rate', 7.77e-05),
+             ('max_grad_norm', 5),
+             ('n_envs', 1),
+             ('n_epochs', 10),
+             ('n_steps', 8),
+             ('n_timesteps', 20000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=-3.29, ortho_init=False)'),
+             ('use_sde', True),
+             ('vf_coef', 0.19),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,73 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - device
+    - auto
+  - - env
+    - MountainCarContinuous-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - n_eval_envs
+    - 1
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3913475051
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3

config.yml

@@ -0,0 +1,33 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - clip_range
+    - 0.1
+  - - ent_coef
+    - 0.00429
+  - - gae_lambda
+    - 0.9
+  - - gamma
+    - 0.9999
+  - - learning_rate
+    - 7.77e-05
+  - - max_grad_norm
+    - 5
+  - - n_envs
+    - 1
+  - - n_epochs
+    - 10
+  - - n_steps
+    - 8
+  - - n_timesteps
+    - 20000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-3.29, ortho_init=False)
+  - - use_sde
+    - true
+  - - vf_coef
+    - 0.19

env_kwargs.yml

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

ppo-MountainCarContinuous-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893202514403c8bda7e82c24302bb82bd118f6815d25ce8d7e4152b6209ca7db
+size 135161

ppo-MountainCarContinuous-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a6

ppo-MountainCarContinuous-v0/data

@@ -0,0 +1,105 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__module__": "stable_baselines3.common.policies",
+        "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\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()`` 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 squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features 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    ",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f85f31d9cb0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f85f31d9d40>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f85f31d9dd0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f85f31d9e60>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f85f31d9ef0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f85f31d9f80>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f85f31e0050>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f85f31e00e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f85f31e0170>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f85f31e0200>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f85f31e0290>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f85f322c6f0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "log_std_init": -3.29,
+        "ortho_init": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVYwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAACamZm/KVyPvZRoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAACamRk/KVyPPZRoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu",
+        "dtype": "float32",
+        "_shape": [
+            2
+        ],
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWV4QsAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAYWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAIC/lGgKSwGFlIwBQ5R0lFKUjARoaWdolGgSKJYEAAAAAAAAAAAAgD+UaApLAYWUaBV0lFKUjA1ib3VuZGVkX2JlbG93lGgSKJYBAAAAAAAAAAGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAYWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYBAAAAAAAAAAGUaCFLAYWUaBV0lFKUjApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBJfX3JhbmRvbXN0YXRlX2N0b3KUk5SMB01UMTk5MzeUhZRSlH2UKIwNYml0X2dlbmVyYXRvcpRoMIwFc3RhdGWUfZQojANrZXmUaBIolsAJAAAAAAAAAAAAgFPCs5yHA7WTcuyrW+jmsvLPtoHa1QbvYaExTaBrtczZE+YYn3SceS/IpRuAxHkBSZ4PQ+Rd4BiTkhNVzNRKKWTSCJW+NNCeRHJ6A/Ctvwpzm3s+6WCxBtp1A0ULbn3WFmrrBDRmg7fz9aUvae9CY0O1XPfCd1LMRkQ3LQiJbtCOrnf7GLaAT3ue+U8y7BLYuY5ehakZyq49di1nK0KAnsXuxx/1IgFdS88kD8wZUmREV5hwnQr1Ehe16VreO8T/Qc86sV+2h90z2FiJqqLNf3s/yZS3bA9DHzGZfRtgkKu3Bx0ZTN7I+466APXPqRreJf4gBqUW/NB248FO9cpD0wFaed9QV63NqpiFOs/RYeEwD8e32dZFRfi9SK5aLvuApJMu2LOfZweypHIkyPjeY5W+tsm2bdPmVoCAOiyi73cf5k0LQeJNWqZU/wuy/f8myghZ9qrjf+2JSJMaB9VNMXWmxuq4Dq0fkhzJr1ML7SgftfSG29O5koFUMozQL58gAzyX96ZMcpWbZ+3/zlaVhGln5egXC8MtIK6xIFCvh/vD/F1jLgYIp14MM597MuPmTpa+OaKek7bql9Cp8/0skhg5QSCvCaijm8wenxrfqLyRxDPCpS+L3isJC5LrjFgWnsdxQXVrJK8uaobJcTIJ5NrYYfA2l5gH27iPI9EqhzFtZJXiE4vXpH18f3kouYV9RowPzOtmYsbmstR/Mx/VY7E0XBmnMidL4dYTUXgxaDbFxWy3y6miL2yw0I2O09vPWV7LqbwMbthlU26lrLfnJDz88B+7y4pFCwvsHgCsMWq6pvroAF4Ms+++JnhzrL0GLrtfJ7667p42Vg78GirmKIRMFH0p6aLRPV4V/fclE3PLBj0InU315M5v7fDFj/IreJeFUhIAy5/BlvLdgwIfBMBWvyjhqGRBo2KmdiDAO9BPhdi6oGmZUCxTDjUyMd8rjeRdntTE+L9sHQUSvUfpRjKcSIjZXcjsMMSwwU0QzIXewD4nZg8EAZ72iHnChWveW7cB5EQRFE+YPvvyNAw4OvORF+DjDtmLUz6jNz0JbkuKbhIQEEVbpDRkoeIGA4HATymZeE4TX/hvhOxJfX5liXD9/Uon8OjJ/hhIrDNUYR2NOV2R1L+VuK/JA9o0izGPiCC9vi7UK1u4re8tvPrBInC6BH2DpMvWSRepdH0frFxGsH/kRB/S77USeMs38a+yorDaa9Wsb9WnuQg10vl087jhvwSZx77fGq52NV1h/UnZAjnqJOjCPBgQrY0wsSeSW6SOSdItAOupiWkVvSzHz+gopd/3FUUPbjdik7Vd6O6ycGOFwp4+wyZqq1MKHww5exJND6De8NB4fGBzsvKoT8O1fAC3Y2Z+3mLYwkCJXULx2zNSO90bQi0L0BhTF1AidNtqRkak72V+V1kos6m4F+kyZiOiwxfcHKWHmpQe3A8HpX6nacx0Zso0WyF/W/sOLo//2g0YD9koIjgKvw//f9Em4CvxNBUMnJYTVQJGysF4QMShnM6byaMNJhRVALf+X0+SgLJkEwLfKdBbKxjA035OEc2YKmUpvooVUUt+9U8d7cKRgNYKKPwCHyYfLJSQt4ZEdThgjeywDxgsGzPax5SklOLroSYn39feofatZDzJXevfPTHyi1ZLwpe6Hwkbqz1FuOnHiShPedbEA9b/HCtBytSZrgUwlwHpQlAiBTSxpN7TFzVZrrhRd6N8W+FeE9SAGCHwXchFR4SCGThPyRGO/XWkMPJ42BLUOmMGepDQgWH646tjoJSE3EXcA5iDS+Nq6Oh521oC2UPAnvxIj1QbVh8IbxlBytRTTjc0c14E9cyhIPlgIoHriuEFSMXSEzOGL1MmL6UCbiXfsRg9Z6OwWCCl3VeGg5bEZ1kjJkvs08k7wtPk4ATAjaTL3QoY2gf106zFbJtL4D5gmLMJ9OuzE2Fn5uaAqqpjXIqqEXxS9jtpsRU9VTHCg68RwXQVIUhuVJgHq8fOigBMrW7Am5+jjo/GNNlcFcp813dFiXy4qHhjGSEjNXp3ln03NZkOgqXQ8SalJlPOvyrAS9wW9EtjQKhcrBSWSsQ8C3o/Mc/sR/CMRB85ZIojR/tiCKtOutxQMIusIOnYHK8g6kPpTQ8J/PfJ8pa3GEoYoA67axQTXsysd2Y6ZDwpz1HkAeISVK2AlCcuQssrQv8dVLAcins/2kjRFp5Vp82HSX9j6Ci9GH5mkdyqV84vWsdwRz4JNXHZoHVZKnrxSdA1HUwRUI/5oWiqnGk9KyiS4Mv9dQIVluJ1+/pAHYEdG9YgLHiNE2zA7aIQbqqlGX6jH1CrHSPL9mnlHdPiKjozwRXu02UQuzlGJn+/PUkU6cPYLLeLc8e7S2qfCZxbdpHioand7wYKqb5bMb8dA3Dwvm6P6iJXSogJ+Q+0z43li8ydYJqZNZlSjsljr/2c5UU33vMhLDLEXIHT8WzrsS45TsKNbhYfTYx6Ds/8W5yOtiOPWc0+fRlAjbQC++FKo5UaMl2eRCxI4U5/heX2HxJGNk50rICjuFsG/8Q+NUuJgS+y3FMhe+sm1e2MdC+ldkBqEn8oRxajECbP4Wizz1tfJliW/1A5fdGTfUxM3HV72bJgnqswmoAumAx6d36KfuZwEEp0/wcrdo+8/unJ5f2mYeqCrOcaxDJrs6SxW1zVaH/YTZl+RNA0NjPLgaqnlveaes/MkpzsVEQDtvKGFrG1cnmGjZVi2azrSDGQ0Y423nEksDC5awYcOJmVYbeA4DkMSNfj+7Dx2SzH/PVPuXLX9aw9K9QF4Ml48zsSrwsVjIa8+gIdffs2pf2wCKcPtFez6vOT0UDuFHknJjMDg0fI3DnyC7jJqO8V4XpmPyarTp3JJRGhmqTHhpZInn70JMfS+RFry5+rLSOM0T+KWV8fYjs9eyCiZijlR4AiADooXm9G8JIzZCLZX2Dty83iyz7gQzSxYO7ULuTT1stvGuJwbBP4LMhLXkbxdhAmBSDiYNOnc3O+yFsO6Ps9UOQD8S4Pbr8hZ4mFjbicpO635SwpmHINYDeuewln3/GHz69LpCjmpnKPeF9ZxXcq6MR4kJUV2j/dQzqjLniNaQmrMkULdI7W1sMXRFcsz9xs1GVwVqmtMVws8HtvXMYNmosCrrgAFX2ghPz7dXCV6vML5YhfNbDAzzG6MHffrslrhMav3vtlt8Fnld4VaH6IhMkowayT1lSVvfvlKHCWwtKaTcOZrR5LZGalJOpFbVIFUOAo+LnY/25bmc3KloyLzgiTudjPsXEGPNPBIvE/5cMEvU4Lrs0N3tCke4abYDXF9f14QrwLlGgHjAJ1NJSJiIeUUpQoSwNoC05OTkr/////Sv////9LAHSUYk1wAoWUaBV0lFKUjANwb3OUTXACdYwJaGFzX2dhdXNzlEsAjAVnYXVzc5RHAAAAAAAAAAB1YnViLg==",
+        "dtype": "float32",
+        "_shape": [
+            1
+        ],
+        "low": "[-1.]",
+        "high": "[1.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 20000,
+    "_total_timesteps": 20000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1653001017.3332515,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVfQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAO8j6r4AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwKGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 0,
+    "use_sde": true,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 25000,
+    "n_steps": 8,
+    "gamma": 0.9999,
+    "gae_lambda": 0.9,
+    "ent_coef": 0.00429,
+    "vf_coef": 0.19,
+    "max_grad_norm": 5,
+    "batch_size": 256,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-MountainCarContinuous-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb435a5401333c9e428ac6b4d4de20678cb4b67ace1bf7655e2051cbf2953ce
+size 77847

ppo-MountainCarContinuous-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d51e8562bf9474172ca37315e7e410ab91e2b18e2b54d2388ea5cbce1a97a3
+size 39742

ppo-MountainCarContinuous-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo-MountainCarContinuous-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.0-110-generic-x86_64-with-debian-bullseye-sid #124-Ubuntu SMP Thu Apr 14 19:46:19 UTC 2022
+Python: 3.7.12
+Stable-Baselines3: 1.5.1a6
+PyTorch: 1.11.0+cpu
+GPU Enabled: False
+Numpy: 1.21.6
+Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e859a0c8e732f071d1c21d572edaaa74d66d97573d77fe09b54b1599904c0b15
+size 229815

results.json

@@ -0,0 +1 @@
+{"mean_reward": 94.57152370000001, "std_reward": 0.4468755932758117, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-20T09:31:37.557384"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c02bd1742d7bb16d035088e757947f1f39a18215879e001497a0632bcef61b
+size 2961