Cheekydave commited on
Commit
95d81dc
1 Parent(s): 6a44dae

Upload PPO CarRacing-v2 trained agent

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: CarRacing-v2
17
  metrics:
18
  - type: mean_reward
19
- value: -93.13 +/- 0.61
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: CarRacing-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: -75.77 +/- 15.73
20
  name: mean_reward
21
  verified: false
22
  ---
config.json CHANGED
The diff for this file is too large to render. See raw diff
 
ppo-CarRacing-v2.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abe3056d1b5165bc01a2080e8ec9dac2c2a520e38ae1d63f528348e11f33b5fc
3
- size 42785398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88311bd2ef907de56c909a46e90135b799f36e9014de619f318434c69f6fb37c
3
+ size 26323560
ppo-CarRacing-v2/data CHANGED
The diff for this file is too large to render. See raw diff
 
ppo-CarRacing-v2/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b84779ea898fa7f9964730b3572f6d66f011e82e2f5dea27b038f78ebb745ea0
3
- size 28391969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c321efadaf8fd511fe25cab1aacba1c61f022295f6777860ee28db3fbceab5a4
3
+ size 17416033
ppo-CarRacing-v2/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc3bda293354a4682f491ce3322f4dd392711c104187432dd8059ed174b4f55e
3
- size 14195503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5ea1d2f2232ad6ab5131dfc410f1e3af2568e957e5682c923a48c69a11e6cb4
3
+ size 8710383
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +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"}
 
1
+ {"mean_reward": -75.76801420000001, "std_reward": 15.732121416788651, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-17T15:07:07.045141"}