pittawat commited on
Commit
7a6febb
·
1 Parent(s): e7c7a31

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: -244.27 +/- 118.52
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,13 +37,13 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 100000
41
- 'learning_rate': 1e-05
42
  'num_envs': 4
43
- 'num_steps': 64
44
  'anneal_lr': True
45
  'gae': True
46
- 'gamma': 0.98
47
  'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'pittawat/LunarLander-v2-ppo'
58
- 'batch_size': 256
59
- 'minibatch_size': 64}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -140.46 +/- 90.33
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
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
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'pittawat/LunarLander-v2-ppo'
58
+ 'batch_size': 512
59
+ 'minibatch_size': 128}
60
  ```
61
 
logs/events.out.tfevents.1676509656.f39059416aa0.6046.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c13875bf9b752ccef6bd0511768351b1f56f66c54ac2d83b64e91ea2b561874d
3
+ size 111161
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30a7434e65bb243040fafe0267d320a521b008fff3172c227a44cf58a9c5a22a
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
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": -244.26997946168194, "std_reward": 118.52077785905594, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T01:05:55.332575"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -140.45658990684834, "std_reward": 90.33446661106434, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T01:08:18.875202"}