Upload PPO CarRacing-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CarRacing-v2
     metrics:
     - type: mean_reward
-      value: -93.13 +/- 0.61
+      value: -75.77 +/- 15.73
       name: mean_reward
       verified: false
 ---

ppo-CarRacing-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abe3056d1b5165bc01a2080e8ec9dac2c2a520e38ae1d63f528348e11f33b5fc
-size 42785398
+oid sha256:88311bd2ef907de56c909a46e90135b799f36e9014de619f318434c69f6fb37c
+size 26323560

ppo-CarRacing-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b84779ea898fa7f9964730b3572f6d66f011e82e2f5dea27b038f78ebb745ea0
-size 28391969
+oid sha256:c321efadaf8fd511fe25cab1aacba1c61f022295f6777860ee28db3fbceab5a4
+size 17416033

ppo-CarRacing-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3bda293354a4682f491ce3322f4dd392711c104187432dd8059ed174b4f55e
-size 14195503
+oid sha256:b5ea1d2f2232ad6ab5131dfc410f1e3af2568e957e5682c923a48c69a11e6cb4
+size 8710383

results.json

@@ -1 +1 @@
-{"mean_reward": -93.1258212, "std_reward": 0.6119614573889092, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-17T14:59:05.203193"}
+{"mean_reward": -75.76801420000001, "std_reward": 15.732121416788651, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-17T15:07:07.045141"}