Schwarzschild009 commited on
Commit
87a7655
·
1 Parent(s): 643870c

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: 35.24 +/- 117.71
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -39,8 +39,8 @@ model-index:
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 1000000
41
  'learning_rate': 0.0001
42
- 'num_envs': 4
43
- 'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Schwarzschild009/hm-ppo-LunarLander-v2'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -22.37 +/- 86.74
21
  name: mean_reward
22
  verified: false
23
  ---
 
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 1000000
41
  'learning_rate': 0.0001
42
+ 'num_envs': 16
43
+ 'num_steps': 256
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Schwarzschild009/hm-ppo-LunarLander-v2'
58
+ 'batch_size': 4096
59
+ 'minibatch_size': 1024}
60
  ```
61
 
logs/events.out.tfevents.1683327892.ef0df3ebac95.23636.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee06680da6cc696929af4bac7dafb96ffa143ea2277d26bae6782623c9121b13
3
+ size 845520
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be67ad34969df73a987879f89a9bd76f48d2293059545666fe68889676e65fcb
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a76a9ebe075e15003a906568d175698752a662e6e98066c1c27b679d3c92e8
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": 35.23643848761948, "std_reward": 117.71001037893492, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-05T22:58:06.832317"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -22.369779199748347, "std_reward": 86.7358430017376, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-05T23:14:16.645458"}