FredericProtat commited on
Commit
d3de44e
1 Parent(s): 1c8726b

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: -204.48 +/- 131.35
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -41,11 +41,11 @@ 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': 0.99
48
- 'gae_lambda': 0.95
49
  'num_minibatches': 4
50
  'update_epochs': 4
51
  'norm_adv': True
@@ -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: -200.64 +/- 119.96
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
48
+ 'gae_lambda': 0.98
49
  'num_minibatches': 4
50
  'update_epochs': 4
51
  'norm_adv': True
 
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.1694528723.7aeeb37fd044.2562.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0617e056faffb14d8768f93c18068ce525c8aa0b444f75ea83f62e026661e1
3
+ size 71323
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c706c81696f37ceaeb74d41e1262ec54c4e2f63b8cbb791c8b01decf796f6a53
3
- size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a88382a16fb1d114b2170d0eb0fa9cfb86ce0da14ec652524a3746a92957c0d6
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": -204.47570223043363, "std_reward": 131.35027984305887, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T10:50:23.964007"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -200.64399301423356, "std_reward": 119.96033592162883, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T14:25:50.888292"}