PhysHunter commited on
Commit
3f37a2b
·
1 Parent(s): ee719ed

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: 168.27 +/- 106.32
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,22 +37,22 @@ model-index:
37
  'torch_deterministic': True
38
  'cuda': True
39
  'record_video': None
40
- 'num_envs': 4
41
  'num_steps': 512
42
  'anneal_lr': True
43
  'gae_lambda': 0.95
44
- 'gamma': 0.99
45
  'num_minibatches': 4
46
- 'update_epochs': 4
47
  'adv_norm': True
48
  'clip_coef': 0.2
49
  'clip_value_loss': True
50
- 'entropy_coef': 0.001
51
  'value_coef': 0.5
52
  'max_grad_norm': 0.5
53
  'target_kl': None
54
  'num_hiddens': 64
55
- 'batch_size': 2048
56
- 'minibatch_size': 512}
57
  ```
58
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 167.54 +/- 39.92
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'torch_deterministic': True
38
  'cuda': True
39
  'record_video': None
40
+ 'num_envs': 16
41
  'num_steps': 512
42
  'anneal_lr': True
43
  'gae_lambda': 0.95
44
+ 'gamma': 0.999
45
  'num_minibatches': 4
46
+ 'update_epochs': 8
47
  'adv_norm': True
48
  'clip_coef': 0.2
49
  'clip_value_loss': True
50
+ 'entropy_coef': 0.01
51
  'value_coef': 0.5
52
  'max_grad_norm': 0.5
53
  'target_kl': None
54
  'num_hiddens': 64
55
+ 'batch_size': 8192
56
+ 'minibatch_size': 2048}
57
  ```
58
 
logs/events.out.tfevents.1686546278.9645607d730a.17342.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c45cb58af5641749037d5e6701d361c68fd4745e790f98980fbdb8062fbb46e5
3
+ size 256000
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f3452322a829abe20f5e50a768c0d9f841abbdd8c47b036f0b9717a854c9550
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b3c0ef9533fbe37d1e2805d0142f43657142d3f7e4e4f9ec1851949e2d626a
3
  size 42597
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": 168.27295381684536, "std_reward": 106.31611966006687, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T05:01:02.701230"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 167.5397378532836, "std_reward": 39.917406084545654, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T05:25:04.559538"}