Corianas commited on
Commit
d783dc2
·
1 Parent(s): 2c5ec66

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: -133.59 +/- 61.55
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,10 +37,10 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': True
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 500000
41
  'learning_rate': 0.00025
42
  'num_envs': 8
43
- 'num_steps': 512
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Corianas/LLander_PPO'
58
- 'batch_size': 4096
59
- 'minibatch_size': 1024}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -106.96 +/- 51.29
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': True
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 300000
41
  'learning_rate': 0.00025
42
  'num_envs': 8
43
+ 'num_steps': 256
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Corianas/LLander_PPO'
58
+ 'batch_size': 2048
59
+ 'minibatch_size': 512}
60
  ```
61
 
logs/events.out.tfevents.1690199551.b3f6f6c97ed0.12461.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a16e6a65d998543119c84f4de12304608951f5e35d7ee38168fed71a054410b
3
+ size 384038
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b78a7312cd50eaf07357bde5d7c0904b0966adf2288b3613fdf725bf2e00480
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:758e71ae69de0f427cf9504921c61c6e3a24046a43e32abf9ff1d061c7b988ca
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": -133.59093298874228, "std_reward": 61.5549071813801, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-24T11:37:23.243509"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -106.96121383773263, "std_reward": 51.294466445435205, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-24T11:55:08.988534"}