a bit more training

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 808.23 +/- 105.55
+      value: 829.71 +/- 50.26
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-CarRacing-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72583967a70584c94194b9d0f02d25d81ea7d1df1596eaa4624b7bb38cffc068
-size 26599906
+oid sha256:0c8034c7486bd055e5c0359e0e2df05fd80563d238c9c9a4d62526a40af3229c
+size 26597790

ppo-CarRacing-v0/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec0d029b873374958d4b7afa685d9de850bab0e049f401bbe3da9967cc2b5aac
+oid sha256:8de8baae8611aa6c0cf45023233991451afa58aa346dcd77c9d9d52d36d61fa7
 size 17424599

ppo-CarRacing-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3cecca2479011a7c3978125e3174507d5711fe27334c716aa88d470fec30e44
+oid sha256:9501574d790e9a80ced1b2636b86b7e3377de7e20f25475b993dcd05a993e57c
 size 8713150

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8437cde6fae99d0048840b2f8b70d6ee8a2ce8a09b8e00ab38deacba6a545e1
-size 939390
+oid sha256:f97b9013556b30d2aefa8c1f2a96bd3aec41dae6d45075e4dd02ed1425f419b6
+size 841747

results.json

@@ -1 +1 @@
-{"mean_reward": 808.2256240002811, "std_reward": 105.55443781784719, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-15T09:21:38.087227"}
+{"mean_reward": 829.7085274964571, "std_reward": 50.263206819596014, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-15T09:28:08.203235"}