yaystevek commited on
Commit
be7da79
1 Parent(s): ce8aa69

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: -162.89 +/- 137.07
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,10 +37,10 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': True
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 50000
41
  'learning_rate': 0.0003
42
  'num_envs': 16
43
- 'num_steps': 1015808
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'yaystevek/LunarLander-v2-scratch'
58
- 'batch_size': 16252928
59
- 'minibatch_size': 4063232}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -83.66 +/- 54.56
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': True
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 1000000
41
  'learning_rate': 0.0003
42
  'num_envs': 16
43
+ 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.999
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'yaystevek/LunarLander-v2-scratch'
58
+ 'batch_size': 16384
59
+ 'minibatch_size': 4096}
60
  ```
61
 
logs/events.out.tfevents.1693536792.3ba86102856c.15713.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:961f961c9fccf853fd17db2b8319265ec2b13973f83b573acbd234e187edc006
3
+ size 1114857
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e541b1708d23f31c9369b677df43ff11571f22fa1554ebef621b3cc7dae1051e
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af043ec7cefa0fca327be8cf9b39a18a2347140ecda7863615dca639bc3b4d13
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": -162.89042521109573, "std_reward": 137.0716392873043, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-01T02:51:45.798182"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -83.66184538224437, "std_reward": 54.55955836127892, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-01T02:59:17.015253"}