First try

.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

Full-Force-MountainCar-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25575ecbe503a000944101e701ab1c35f0d46b3e27952fd97470541bb195cb5e
+size 131834

Full-Force-MountainCar-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.0

Full-Force-MountainCar-v0/data

@@ -0,0 +1,94 @@
+{
+    "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 0x7fcdf1a48c20>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcdf1a48cb0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcdf1a48d40>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcdf1a48dd0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fcdf1a48e60>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fcdf1a48ef0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcdf1a48f80>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fcdf1a4f050>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcdf1a4f0e0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcdf1a4f170>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcdf1a4f200>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fcdf1a8acf0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "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.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 3,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 311296,
+    "_total_timesteps": 300000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1652718290.523141,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAA0b7b4yRje7kjvnvvs/BjykvRu/26koPDKY9L5NB9g7MuoHv1JHozmFtAa/WS38OxUvBb/zIfa6Gd8XvwtrMDzlbwO/cF+BOysW9b5Xjqi6skIEv79vojt+bP++8Wfcu4MgJ7/SagO8CtwKv4p+kLsWQuy+F0JdPCLHvb7aaIo8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.037653333333333316,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 190,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.99,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 34,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

Full-Force-MountainCar-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353e294b20a77c2f50153ed7cef332d031e2edd2aaf3f16993f067c073d2792b
+size 78237

Full-Force-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ed1d20feb826846d370e6b81bfa25e0e76682f654047b6b0c06da37f3f7329
+size 39873

Full-Force-MountainCar-v0/pytorch_variables.pth

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

Full-Force-MountainCar-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
+Python: 3.7.13
+Stable-Baselines3: 1.5.0
+PyTorch: 1.11.0+cu113
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.21.0

README.md

@@ -0,0 +1,28 @@
+---
+library_name: stable-baselines3
+tags:
+- MountainCar-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -200.00 +/- 0.00
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCar-v0
+      type: MountainCar-v0
+---
+
+  # **PPO** Agent playing **MountainCar-v0**
+  This is a trained model of a **PPO** agent playing **MountainCar-v0** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+  
+  ## Usage (with Stable-baselines3)
+  TODO: Add your code
+  

config.json

@@ -0,0 +1 @@
+{"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 0x7fcdf1a48c20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcdf1a48cb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcdf1a48d40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcdf1a48dd0>", "_build": "<function ActorCriticPolicy._build at 0x7fcdf1a48e60>", "forward": "<function ActorCriticPolicy.forward at 0x7fcdf1a48ef0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcdf1a48f80>", "_predict": "<function ActorCriticPolicy._predict at 0x7fcdf1a4f050>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcdf1a4f0e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcdf1a4f170>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcdf1a4f200>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fcdf1a8acf0>"}, "verbose": 1, "policy_kwargs": {}, "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.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLA4wGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 3, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 311296, "_total_timesteps": 300000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652718290.523141, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAA0b7b4yRje7kjvnvvs/BjykvRu/26koPDKY9L5NB9g7MuoHv1JHozmFtAa/WS38OxUvBb/zIfa6Gd8XvwtrMDzlbwO/cF+BOysW9b5Xjqi6skIEv79vojt+bP++8Wfcu4MgJ7/SagO8CtwKv4p+kLsWQuy+F0JdPCLHvb7aaIo8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.037653333333333316, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 190, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.99, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 34, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f99a2fcdf095ba16b249c809c87c242ce88c349046f7be117b6de6606ade57d
+size 202788

results.json

@@ -0,0 +1 @@
+{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-16T16:38:13.375255"}