irow commited on
Commit
639a350
1 Parent(s): 7aa0c2f

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: -86.04 +/- 39.36
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,10 +37,10 @@ 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': 8
43
- 'num_steps': 256
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': 'irow/ppo-LunarLander-v2'
58
- 'batch_size': 2048
59
- 'minibatch_size': 512}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -30.44 +/- 48.27
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 250000
41
  'learning_rate': 0.00025
42
+ 'num_envs': 4
43
+ 'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'irow/ppo-LunarLander-v2'
58
+ 'batch_size': 512
59
+ 'minibatch_size': 128}
60
  ```
61
 
logs/events.out.tfevents.1684422738.irow-pc.65119.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:616f601a2237fe68b3fd6dd95c3b6c5c15ab23b232cf795f149943c0f4ad63c4
3
+ size 400097
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9c92abc168fadd69c76475eba34a091b31f41cc5cbb0c7680e3ea2fa1c4d6f1
3
  size 42817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12ed0921b7b02109ed65fc4ec546fd264e6362e91035045cf295fe896d12a2d8
3
  size 42817
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": -86.03697053584682, "std_reward": 39.36042232207255, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-18T09:06:13.767955"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -30.443244319799454, "std_reward": 48.265887924244666, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-18T09:15:14.467094"}