Zaleks commited on
Commit
042f98b
·
1 Parent(s): cf9ffd7

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: 29.07 +/- 130.86
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,16 +37,16 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 1000000
41
  'learning_rate': 0.00025
42
- 'num_envs': 4
43
- 'num_steps': 256
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
  'gae_lambda': 0.95
48
  'num_minibatches': 4
49
- 'update_epochs': 10
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Zaleks/ppo2-LunarLander-v2'
58
- 'batch_size': 1024
59
- 'minibatch_size': 256}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -74.05 +/- 70.28
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 100000
41
  'learning_rate': 0.00025
42
+ 'num_envs': 16
43
+ 'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
  'gae_lambda': 0.95
48
  'num_minibatches': 4
49
+ 'update_epochs': 16
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Zaleks/ppo2-LunarLander-v2'
58
+ 'batch_size': 2048
59
+ 'minibatch_size': 512}
60
  ```
61
 
logs/events.out.tfevents.1685711201.DESKTOP-FRL08E4.16936.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae8b13847dd9f0b0d795cb51b1cb0e8870db46bef6b2817559702c2a2729d2b2
3
+ size 25391
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:272bedc2d02188e4fc418c060c7080064b856713a2b3bed5a696b2235f64933c
3
  size 42469
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d247db3dc2cf61d76ae96ed458fad59caf7f1f792e35d2f278742d376f7944e0
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": 29.074010649450294, "std_reward": 130.86442196041534, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-25T20:40:37.078225"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -74.04791778132294, "std_reward": 70.28427089197578, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-02T15:07:32.197298"}