FredericProtat commited on
Commit
cf04ba4
1 Parent(s): fa41cfc

Push agent to the Hub

Browse files
README.md CHANGED
@@ -17,7 +17,7 @@ model-index:
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
- value: -126.11 +/- 43.68
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -41,7 +41,7 @@ model-index:
41
  'capture_video': False
42
  'env_id': 'LunarLander-v2'
43
  'num_envs': 4
44
- 'num_steps': 256
45
  'anneal_lr': True
46
  'gae': True
47
  'gamma': 0.999
@@ -56,7 +56,7 @@ model-index:
56
  'max_grad_norm': 0.5
57
  'target_kl': None
58
  'repo_id': 'FredericProtat/ppo-LunarLander-v2'
59
- 'batch_size': 1024
60
- 'minibatch_size': 256}
61
  ```
62
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -139.00 +/- 51.54
21
  name: mean_reward
22
  verified: false
23
  ---
 
41
  'capture_video': False
42
  'env_id': 'LunarLander-v2'
43
  'num_envs': 4
44
+ 'num_steps': 512
45
  'anneal_lr': True
46
  'gae': True
47
  'gamma': 0.999
 
56
  'max_grad_norm': 0.5
57
  'target_kl': None
58
  'repo_id': 'FredericProtat/ppo-LunarLander-v2'
59
+ 'batch_size': 2048
60
+ 'minibatch_size': 512}
61
  ```
62
 
logs/events.out.tfevents.1694611922.9f4ebd18e9a9.8894.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f1daf0bd6c195a211bee8095a3647e83c6f2b395636167efb962c9941f13896
3
+ size 150215
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb39ce9580cc067bb8dba6b23c37848196e7e1ce4c8bfdc538ddc2c4e5896b44
3
  size 42469
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5491984446f5c291d67e7420275d6b388f4355d4765ece7b0465e4520b868d1
3
  size 42469
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "LunarLander-v2", "mean_reward": -126.11117655502812, "std_reward": 43.67537665875438, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T13:20:34.805695"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -139.00069145324463, "std_reward": 51.535805780681976, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T13:33:00.172169"}