29thDay commited on
Commit
9938a1c
·
1 Parent(s): 9c94aa6

Upload PPO CartPole-v1 trained agent

Browse files
Files changed (4) hide show
  1. PPO-CartPole-v1.zip +1 -1
  2. README.md +1 -1
  3. replay.mp4 +0 -0
  4. results.json +1 -1
PPO-CartPole-v1.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab7213ec57edc60862216df5ec7f5daed08fcf25a3c19714ee9d9cf853ca73af
3
  size 53698
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c187f7a37caef58a14d83fc8479ec13d6e968f2bce8ea01092839690a35f730
3
  size 53698
README.md CHANGED
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: 385.90 +/- 176.13
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 295.40 +/- 204.73
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 385.9, "std_reward": 176.1252111425278, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-04T13:10:40.825049"}
 
1
+ {"mean_reward": 295.4, "std_reward": 204.72967542591377, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-04T13:12:25.453815"}