charlieoneill commited on
Commit
3a3dd56
1 Parent(s): 1dd25c7

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: -115.94 +/- 58.19
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,15 +37,15 @@ model-index:
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': 4
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': 4
50
  'norm_adv': True
51
  'clip_coef': 0.2
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'charlieoneill/ppo-CartPole-v1'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 115.78 +/- 92.11
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': 0.00025
42
  'num_envs': 4
43
+ 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
+ 'gae_lambda': 0.98
48
+ 'num_minibatches': 64
49
  'update_epochs': 4
50
  'norm_adv': True
51
  'clip_coef': 0.2
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'charlieoneill/ppo-CartPole-v1'
58
+ 'batch_size': 4096
59
+ 'minibatch_size': 64}
60
  ```
61
 
logs/events.out.tfevents.1684216191.935e5cd9caa6.16892.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a99b2a6b2a76152a5fbb41b3386d3a5c5106479806f5f5cfdc0946b97dbbeb2e
3
+ size 349258
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8802a401f9eedb07ef810eb6d49c91ffd77d753bd96675776004777157abd97e
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8111d9294f87fe466572ab15df23f12adf7bfeaee724f58f2d72b048f1dee15d
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": -115.9359415944134, "std_reward": 58.185936979026906, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-16T05:46:04.252897"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 115.78487168267627, "std_reward": 92.1056038588687, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-16T06:19:07.243602"}