kieranbm commited on
Commit
7363c75
1 Parent(s): 027b322

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: -141.12 +/- 82.95
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -40,22 +40,22 @@ model-index:
40
  'total_timesteps': 50000
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
52
  'clip_vloss': True
53
- 'ent_coef': 0.01
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'kieranbm/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: -136.99 +/- 80.74
21
  name: mean_reward
22
  verified: false
23
  ---
 
40
  'total_timesteps': 50000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
+ 'num_steps': 512
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
+ 'gae_lambda': 0.9
48
  'num_minibatches': 4
49
+ 'update_epochs': 10
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
53
+ 'ent_coef': 0.011
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'kieranbm/ppo-LunarLander-v2'
58
+ 'batch_size': 2048
59
+ 'minibatch_size': 512}
60
  ```
61
 
logs/events.out.tfevents.1707259660.b93bc0e56554.6423.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b14571f9b9502f896480feb6d46a1e59ce6c681b310ade0e9f9103ec602e98c
3
+ size 65551
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38c0ef9861c7c50c0681c7722755c4b5c2db04a7ed9b1e1405b378686611573b
3
  size 43026
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": -141.117700256993, "std_reward": 82.95203101002005, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-06T13:08:40.599746"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -136.99292616978218, "std_reward": 80.74059544156171, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-06T22:48:20.000827"}