Yanrds commited on
Commit
42e089a
·
1 Parent(s): bc35c4d

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: -57.64 +/- 61.11
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -39,13 +39,13 @@ model-index:
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 1000000
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': 'Yanrds/ppo-LunarLander-v2-from-scratch'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 116.20 +/- 63.15
21
  name: mean_reward
22
  verified: false
23
  ---
 
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 1000000
41
  'learning_rate': 0.00025
42
+ 'num_envs': 16
43
+ 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.999
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': 'Yanrds/ppo-LunarLander-v2-from-scratch'
58
+ 'batch_size': 16384
59
+ 'minibatch_size': 256}
60
  ```
61
 
logs/events.out.tfevents.1681868453.15af5fbffb08.7953.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56c303daa694e374f30a2ea3185d497566c368a6e3275ea969e3ac7fdd981779
3
+ size 352635
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d3e4c679fa6fadd5f17062c557e054db3e1716d87d7b6f6bcaf662427972168
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e30ad109ec0dc4a69b3a5932b03669f66aeae9cbd6934683c314f94ae2b2a6c2
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": -57.636142424268726, "std_reward": 61.10504077356268, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-18T23:50:31.271065"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 116.20295874551138, "std_reward": 63.14954728153944, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-19T01:59:30.926253"}