Cheekydave commited on
Commit
24d308b
1 Parent(s): 7420e46

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: 56.32 +/- 35.69
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: CarRacing-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: -63.73 +/- 2.13
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 sha256:149fa9c9cd45d4123eb5b038e3ed62ac7691c60f6695a785877792420f78305f
3
- size 26323576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f82a7462868fad61fa9ae5d6e722bb8fd3062780f45acfb1fcabbc86d075b1ed
3
+ size 26327679
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 sha256:2ad1713a43bae37f222a58839f50b2f05f769e8e091f3c8f7a218fa53c49d7c3
3
  size 17416033
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c1cee97133d770254234bd2572303c4c1abb9508f2a24fe47ca11792171095
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:b932caafa555d4fedb0916465441e71dec2b71f5c49595d234c8a3de1e8f964a
3
  size 8710383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cbbced99c5af6a7bff1363c994562beff57c1fbf0a601893fe31c8f4184c53f
3
  size 8710383
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:005b0fc17b51c96b5a540f319c2a41d316e7f0b90fd552caa8aa7f55d013b1c6
3
- size 466355
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70030481c925292ed26c63c3e4ab6bb0afadeec6ab01791d08148827224b63f3
3
+ size 227882
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 56.3192213, "std_reward": 35.68732608885631, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-23T10:01:06.854190"}
 
1
+ {"mean_reward": -63.7287727, "std_reward": 2.1289086971368225, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-23T16:05:33.296900"}