FredericProtat commited on
Commit
8960ab9
1 Parent(s): 2d84980

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: -132.04 +/- 71.07
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': 128
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': 512
60
- 'minibatch_size': 128}
61
  ```
62
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -104.13 +/- 67.22
21
  name: mean_reward
22
  verified: false
23
  ---
 
41
  'capture_video': False
42
  'env_id': 'LunarLander-v2'
43
  'num_envs': 4
44
+ 'num_steps': 1024
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': 4096
60
+ 'minibatch_size': 1024}
61
  ```
62
 
logs/events.out.tfevents.1694552159.17a722d28ef8.8510.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2a3c346952a40390e31310acdd5a6385c43d4d52978512a920169a8c9e583ba
3
+ size 141109
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b6fc3e32b48291e5f435c30faae18c9cc71fb6911b747cbee983325fe77dbf9
3
  size 42469
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ebf3465c38ec32051261e720f626890cc85ca8688e353209b67003d4a9114ce
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": -132.03725269892158, "std_reward": 71.07413500134216, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T20:52:55.455294"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -104.12801344783134, "std_reward": 67.21761600900672, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T20:56:59.871915"}