Hans14 commited on
Commit
d9e7b0c
·
1 Parent(s): 1b72f58

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: -61.05 +/- 101.92
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,14 +37,14 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 500000
41
  'learning_rate': 0.0001
42
  'num_envs': 4
43
- 'num_steps': 512
44
  'anneal_lr': True
45
  'gae': True
46
- 'gamma': 0.95
47
- 'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': 0.015
57
  'repo_id': 'Hans14/LunarLander-v2'
58
- 'batch_size': 2048
59
- 'minibatch_size': 512}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -97.43 +/- 97.59
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 1000000
41
  'learning_rate': 0.0001
42
  'num_envs': 4
43
+ 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.999
47
+ 'gae_lambda': 0.98
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': 0.015
57
  'repo_id': 'Hans14/LunarLander-v2'
58
+ 'batch_size': 4096
59
+ 'minibatch_size': 1024}
60
  ```
61
 
logs/events.out.tfevents.1689494020.8981986e6198.45638.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:144678449055db209c33d7e46532746ec432aa36c62719a9174ab62e73431017
3
+ size 1257771
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8345e8738962770f40cffe2c5725fcb424206d75f17a3287ee361a20bd1a25d3
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c48f6208ebe071d7e7badece59a87158bc48db215e0d3245f9f4400fb72108e0
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": -61.05257374377165, "std_reward": 101.91741754558755, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-16T07:48:42.044325"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -97.43019659975843, "std_reward": 97.58500382569524, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-16T08:06:47.443764"}