Initial commit

ppo-seals-MountainCar-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfbcacb6e742fc516977dd67cb70fc46d628094425403ed4180fd8bddf48734c
-size 135108
+oid sha256:a1954ebe2f0e8c13dff2ea4f1f7a3b360b5ac45edceae25242c3ed04fc6183e9
+size 135328

ppo-seals-MountainCar-v0/data

@@ -3,10 +3,10 @@
         ":type:": "<class 'abc.ABCMeta'>",
         ":serialized:": "gAWVRwAAAAAAAACMF2ltaXRhdGlvbi5wb2xpY2llcy5iYXNllIwnTWxwUG9saWN5V2l0aE5vcm1hbGl6ZUZlYXR1cmVzRXh0cmFjdG9ylJOULg==",
         "__module__": "imitation.policies.base",
-        "__init__": "<function MlpPolicyWithNormalizeFeaturesExtractor.__init__ at 0x7fe3c60d1940>",
-        "__doc__": null,
+        "__doc__": "An ActorCriticPolicy that uses a NormalizeFeaturesExtractor by default.\n\n    Note: this policy is used when training the expert models using the rl-zoo3 to\n    ensure that the observations are normalized properly.\n    ",
+        "__init__": "<function MlpPolicyWithNormalizeFeaturesExtractor.__init__ at 0x7f770713baf0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7fe3c6120210>"
+        "_abc_impl": "<_abc_data object at 0x7f7707185360>"
     },
     "verbose": 1,
     "policy_kwargs": {

results.json

@@ -1 +1 @@
-{"mean_reward": -100.6, "std_reward": 5.748043145279966, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-11-16T15:00:28.926124"}
+{"mean_reward": -100.6, "std_reward": 5.748043145279966, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-11-16T16:05:57.962051"}