VAZaytsev commited on
Commit
b6d0a2a
·
1 Parent(s): 5367f01

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: -153.50 +/- 62.94
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': 4
43
- 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'VAZaytsev/ppo_LL_v2'
58
- 'batch_size': 4096
59
- 'minibatch_size': 1024}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -140.61 +/- 52.20
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 150000
41
+ 'learning_rate': 0.00015
42
  'num_envs': 4
43
+ 'num_steps': 512
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.999
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'VAZaytsev/ppo_LL_v2'
58
+ 'batch_size': 2048
59
+ 'minibatch_size': 512}
60
  ```
61
 
logs/events.out.tfevents.1678633192.d093eede9204.13760.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d997aabebfdf96677558cb60b714b8a903ec741bad2582911df2e9bcfdac8d
3
+ size 221144
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd17169d50c310c34e832e06bdb0ce71a2f0305481641bfb3cbdbf96b2337600
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5a0c446f7ac78db62101bd219c08b14cc9e88bce57f62d429475e1c309cf843
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": -153.50081018979466, "std_reward": 62.941880464471375, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T14:52:16.481531"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -140.61214838128137, "std_reward": 52.19921829475419, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T15:01:46.269995"}