Initial commit

.gitattributes

@@ -25,3 +25,5 @@ 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
+vec_normalize.pkl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+library_name: stable-baselines3
+tags:
+- AntBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 2519.30 +/- 10.68
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: AntBulletEnv-v0
+      type: AntBulletEnv-v0
+---
+
+# **A2C** Agent playing **AntBulletEnv-v0**
+This is a trained model of a **A2C** 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 a2c --env AntBulletEnv-v0 -orga sb3 -f logs/
+python enjoy.py --algo a2c --env AntBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo a2c --env AntBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo a2c --env AntBulletEnv-v0 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('ent_coef', 0.0),
+             ('gae_lambda', 0.9),
+             ('gamma', 0.99),
+             ('learning_rate', 'lin_0.00096'),
+             ('max_grad_norm', 0.5),
+             ('n_envs', 4),
+             ('n_steps', 8),
+             ('n_timesteps', 2000000.0),
+             ('normalize', True),
+             ('normalize_advantage', False),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=-2, ortho_init=False)'),
+             ('use_rms_prop', True),
+             ('use_sde', True),
+             ('vf_coef', 0.4),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

a2c-AntBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b91454ba0bf387c1a186d2dbb764f8a0c4d61badea7913fdd2c054ccb490a59
+size 133608

a2c-AntBulletEnv-v0/_stable_baselines3_version

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

a2c-AntBulletEnv-v0/data

@@ -0,0 +1,106 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__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 0x7fdc739f3950>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fdc739f39e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fdc739f3a70>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fdc739f3b00>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fdc739f3b90>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fdc739f3c20>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fdc739f3cb0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fdc739f3d40>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fdc739f3dd0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fdc739f3e60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fdc739f3ef0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fdc73a44840>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gASVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu",
+        "log_std_init": -2,
+        "ortho_init": false,
+        "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
+        "optimizer_kwargs": {
+            "alpha": 0.99,
+            "eps": 1e-05,
+            "weight_decay": 0
+        }
+    },
+    "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]",
+        "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]",
+        "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]",
+        "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]",
+        "_np_random": null,
+        "_shape": [
+            28
+        ]
+    },
+    "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": 4,
+    "num_timesteps": 2000000,
+    "_total_timesteps": 2000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614621275.348317,
+    "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": null,
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_episode_num": 0,
+    "use_sde": true,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVRAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQKJwSMsH0K+MAWyUTegDjAF0lEdAwV6lz4DcM3V9lChoBkdAop32hwl0HWgHTegDaAhHQMFeswd0aIh1fZQoaAZHQKKrWsLfDUFoB03oA2gIR0DBX24/X5FgdX2UKGgGR0CiyQkYXO4YaAdN6ANoCEdAwV/wE6DGtXV9lChoBkdAokkVyPuG9GgHTegDaAhHQMFkYWbwz+F1fZQoaAZHQKJAZev6j35oB03oA2gIR0DBZG6YgJTmdX2UKGgGR0CiOaVC5VfeaAdN6ANoCEdAwWUqtbLU1HV9lChoBkdAophZ2MbWE2gHTegDaAhHQMFlrerU9ZB1fZQoaAZHQKGVPEcbR4RoB03oA2gIR0DBaiC3qiXZdX2UKGgGR0CiPtjXnQpnaAdN6ANoCEdAwWot+98JD3V9lChoBkdAorNU9Mbm2mgHTegDaAhHQMFq6rB0p3J1fZQoaAZHQKIyaE6DGtJoB03oA2gIR0DBdHC+QEIPdX2UKGgGR0Ch2ynBciW3aAdN6ANoCEdAwXjglIEr5XV9lChoBkdAofzmKbayr2gHTegDaAhHQMF47Q4bS7Z1fZQoaAZHQKG7vIp6QeVoB03oA2gIR0DBeao20iQldX2UKGgGR0CiYpTlLeyiaAdN6ANoCEdAwXosqzZ6EHV9lChoBkdAossUmrsByWgHTegDaAhHQMF+npHiFTN1fZQoaAZHQKI90UC7sfJoB03oA2gIR0DBfqujdpIudX2UKGgGR0CiT3l54W1uaAdN6ANoCEdAwX9m0DU3GXV9lChoBkdAol0fKGL1mWgHTegDaAhHQMF/6I2fkFR1fZQoaAZHQKLMLeSB9ThoB03oA2gIR0DBjVdD8cdYdX2UKGgGR0CicljBEa2naAdN6ANoCEdAwY1ji3ocJnV9lChoBkdAohnvHaN+9mgHTegDaAhHQMGOHtnoPkJ1fZQoaAZHQKHoT/KhcqxoB03oA2gIR0DBjqBFgDzRdX2UKGgGR0Ch+2aRhc7haAdN6ANoCEdAwZMPVQQ+U3V9lChoBkdAonbzqnm7rmgHTegDaAhHQMGTG73fygB1fZQoaAZHQKJj7n2ZiNNoB03oA2gIR0DBk9fOpsGgdX2UKGgGR0ChLQB2GIsRaAdN6ANoCEdAwZRZyTY/V3V9lChoBkdAola1toBaLWgHTegDaAhHQMGYyzH80k51fZQoaAZHQJ6+GDh99c9oB03oA2gIR0DBmNgjGDL9dX2UKGgGR0Cihh2jXWe6aAdN6ANoCEdAwZmTmEGqxXV9lChoBkdAoeB/bAUL2GgHTegDaAhHQMGjFbPppvh1fZQoaAZHQKH/wGC7K7toB03oA2gIR0DBp4PH7xd6dX2UKGgGR0ChR6N0vGp/aAdN6ANoCEdAwaeQuyNXHXV9lChoBkdAoFRNE9dNWWgHTegDaAhHQMGoTFar3kB1fZQoaAZHQKGsg9ic5KhoB03oA2gIR0DBqM26GxlhdX2UKGgGR0Chfko/iYLLaAdN6ANoCEdAwa08xQBPsXV9lChoBkdAonGWuvECNmgHTegDaAhHQMGtSeP7vXt1fZQoaAZHQKKEGsbvPTpoB03oA2gIR0DBrgWicoYvdX2UKGgGR0ChsUMolUqAaAdN6ANoCEdAwa6HUgB91HV9lChoBkdAoukuN70Fr2gHTegDaAhHQMG78butwJh1fZQoaAZHQKKHNX6InBtoB03oA2gIR0DBu/7mdRR/dX2UKGgGR0ChZRwr1/UfaAdN6ANoCEdAwby6gbp/w3V9lChoBkdAolppx3mmtWgHTegDaAhHQMG9PJgLJCB1fZQoaAZHQKJR8ZlWfbtoB03oA2gIR0DBwa3u7YkFdX2UKGgGR0Ch7SiPZIxyaAdN6ANoCEdAwcG6jxCpm3V9lChoBkdAoxkbZlFtsWgHTegDaAhHQMHCdxP420l1fZQoaAZHQKBYwqI7/4toB03oA2gIR0DBwvkJUo8ZdX2UKGgGR0Ch1S150KZ2aAdN6ANoCEdAwcdp8P4EfXV9lChoBkdAoo3gW3z+WGgHTegDaAhHQMHHdttqHoJ1fZQoaAZHQKGKqCL/CIloB03oA2gIR0DByDIvHtF8dX2UKGgGR0ChuIsspXp4aAdN6ANoCEdAwdGyHHmzSnV9lChoBkdAouTGgFotc2gHTegDaAhHQMHWI0Hpr1x1fZQoaAZHQKFwzdqtYCBoB03oA2gIR0DB1i/NFBppdX2UKGgGR0ChfBxJ2+wlaAdN6ANoCEdAwdbrY7JXAHV9lChoBkdAoihnBk7OmmgHTegDaAhHQMHXbZZ0Syt1fZQoaAZHQKJINRZU1htoB03oA2gIR0DB29ysEJSjdX2UKGgGR0Cibr/thNM5aAdN6ANoCEdAwdvpSvTw2HV9lChoBkdAoiig46wMY2gHTegDaAhHQMHcpL3K0Up1fZQoaAZHQKIsfPpIMBpoB03oA2gIR0DB3SaGgzxgdX2UKGgGR0CjGSi+lCTmaAdN6ANoCEdAweqStHQQc3V9lChoBkdAokFT4QBgeGgHTegDaAhHQMHqnzRIBil1fZQoaAZHQKKKlRIBikRoB03oA2gIR0DB61qvq1PWdX2UKGgGR0CiEWHkDIRzaAdN6ANoCEdAwevb/FR51XV9lChoBkdAotkYHNX5nGgHTegDaAhHQMHwTOLR8dB1fZQoaAZHQKKSYE6DGtJoB03oA2gIR0DB8Flct5D7dX2UKGgGR0CivuNKIznBaAdN6ANoCEdAwfEUiudPL3V9lChoBkdAoctf7WNFSmgHTegDaAhHQMHxl3BP9DR1fZQoaAZHQKKJTlbu+h5oB03oA2gIR0DB9gP9Hc1wdX2UKGgGR0CioGYYixFBaAdN6ANoCEdAwfYRM495hXV9lChoBkdAosvhH3Dej2gHTegDaAhHQMH2zXq7iAF1fZQoaAZHQKHlEHWz4UNoB03oA2gIR0DCAEpSP2f1dX2UKGgGR0ChwFU3XI2gaAdN6ANoCEdAwgS5fE4vOHV9lChoBkdAoNDnY8Md92gHTegDaAhHQMIExgxBVuJ1fZQoaAZHQKGv4ZwXIltoB03oA2gIR0DCBYInndO7dX2UKGgGR0ChXALXUYsNaAdN6ANoCEdAwgYDqynk1nV9lChoBkdAole8dT5wfmgHTegDaAhHQMIKdTuv2Xd1fZQoaAZHQKHlhyHVPN5oB03oA2gIR0DCCoGyVv/BdX2UKGgGR0CiINo2GZeBaAdN6ANoCEdAwgs9P7el9HV9lChoBkdAohjia/h2n2gHTegDaAhHQMILvw+2Vml1fZQoaAZHQKKSnPnjhk1oB03oA2gIR0DCGSlcry2AdX2UKGgGR0Cg8ypf6XSjaAdN6ANoCEdAwhk1+EytWHV9lChoBkdAorxO3+dbxGgHTegDaAhHQMIZ8fJNj9Z1fZQoaAZHQKHNNvIfbK1oB03oA2gIR0DCGnSnLq2SdX2UKGgGR0CioOKwIMScaAdN6ANoCEdAwh7lDcdo4HV9lChoBkdAoWDcPhAGCGgHTegDaAhHQMIe8j+zdDZ1fZQoaAZHQKIhHFWGRFJoB03oA2gIR0DCH63DR+jNdX2UKGgGR0CiQ1FBY3efaAdN6ANoCEdAwiAvPWQOnXV9lChoBkdAolUh/y5I6WgHTegDaAhHQMIknmSpzcR1fZQoaAZHQKHZphDw6QxoB03oA2gIR0DCJKs9r434dX2UKGgGR0Cijwt34bjtaAdN6ANoCEdAwiVmzlcQiHV9lChoBkdAofWlUZNwi2gHTegDaAhHQMIu4dJjDsN1fZQoaAZHQKJn1J8OTaFoB03oA2gIR0DCM1Q/xDsudX2UKGgGR0Cc4irMTviMaAdN6ANoCEdAwjNheyAxz3V9lChoBkdAontA2AG0NWgHTegDaAhHQMI0HZIQOFx1fZQoaAZHQKJkUsMiKSBoB03oA2gIR0DCNJ+s7uD0dX2UKGgGR0Cg2nL0aqCIaAdN6ANoCEdAwjkUCtA9m3V9lChoBkdAok2Ip2ECeWgHTegDaAhHQMI5ILgn+hp1fZQoaAZHQKIhHu0kWyloB03oA2gIR0DCOdxEx7AtdX2UKGgGR0Cijrpb2USqaAdN6ANoCEdAwjpeabWmQHVlLg=="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 62500,
+    "n_steps": 8,
+    "gamma": 0.99,
+    "gae_lambda": 0.9,
+    "ent_coef": 0.0,
+    "vf_coef": 0.4,
+    "max_grad_norm": 0.5,
+    "normalize_advantage": false,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVjAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwSFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDBAAAAACUdJRiLg=="
+    }
+}

a2c-AntBulletEnv-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b7458f0d94585fbcde0bba967187e73a699826d7419900c6d3aa7a204284f4
+size 56126

a2c-AntBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9348bc60253a75e4dfa07cddd2eb534c7298dcff7b222ce5d5a4e6124459d0ae
+size 56766

a2c-AntBulletEnv-v0/pytorch_variables.pth

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

a2c-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

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - a2c
+  - - 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
+    - 2430956467
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,31 @@
+!!python/object/apply:collections.OrderedDict
+- - - ent_coef
+    - 0.0
+  - - gae_lambda
+    - 0.9
+  - - gamma
+    - 0.99
+  - - learning_rate
+    - lin_0.00096
+  - - max_grad_norm
+    - 0.5
+  - - n_envs
+    - 4
+  - - n_steps
+    - 8
+  - - n_timesteps
+    - 2000000.0
+  - - normalize
+    - true
+  - - normalize_advantage
+    - false
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-2, ortho_init=False)
+  - - use_rms_prop
+    - true
+  - - use_sde
+    - true
+  - - vf_coef
+    - 0.4

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49de3f9de3334d48bcad3a9d265ddfe3da0323bde49f6019972fbe76a5dac952
+size 1289690

results.json

@@ -0,0 +1 @@
+{"mean_reward": 2519.3013563, "std_reward": 10.676143120649913, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T17:19:30.038966"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e37e15ae354e461c5509ce16c38c6fe696589f331ef168cfaac47d0b659dedd
+size 98305

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6749c595877c40d02243d362215d10c0dcc9e36633f61a0e8a5d7011f56f105
+size 5504