JessiCega commited on
Commit
6cd5d36
·
verified ·
1 Parent(s): 14e5591

Upload PPO CartRacing-v3 trained agent

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: CarRacing-v3
17
  metrics:
18
  - type: mean_reward
19
- value: 48.66 +/- 33.72
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: CarRacing-v3
17
  metrics:
18
  - type: mean_reward
19
+ value: -75.94 +/- 2.03
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-v3.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:895725bf54f77056363741f9a9d4de37e0264a3d4f0acf2250bf74482714e187
3
  size 43347215
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4cee4bc889eaa5b80a07b3b9b0774589b2b014194c2ad5540c8743a86505cbb
3
  size 43347215
ppo-CarRacing-v3/data CHANGED
The diff for this file is too large to render. See raw diff
 
ppo-CarRacing-v3/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:486d19cd8efc6a21738128d74a7d27ff448fcb0bbacdd11b21d5e6cf6a4df256
3
  size 28392494
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dbd80df1598a860fe07c9f9b5e914496fae4795154530ea6624a7a470750eea
3
  size 28392494
ppo-CarRacing-v3/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9072d1da493d090e5460d79e6cffb7e362a63773ca886e4dc2a4dd55edc962a
3
  size 14195836
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fdfb3ebe054bd6cd497f5ad9dccb32a6a5412b81110beebc528edcebb81c8a9
3
  size 14195836
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4da33daed7a4b0a8a46b52f4cc35bce26479cedad91740d6ab2f942483f350c9
3
- size 479320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e14acf0cf924a3cb03674310aa84b5023483506afd2914d755069931853adb68
3
+ size 1136580
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 48.6579870544374, "std_reward": 33.723589850792926, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-08T18:57:43.960572"}
 
1
+ {"mean_reward": -75.9350241214037, "std_reward": 2.0320921293073955, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-14T03:28:31.631777"}