gstaff commited on
Commit
42b85d7
·
1 Parent(s): a0985d6

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: 123.45 +/- 107.21
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': 2000000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
- 'num_steps': 128
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': 'gstaff/ppo-LunarLander-v2'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -15.48 +/- 56.92
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 1000000
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
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'gstaff/ppo-LunarLander-v2'
58
+ 'batch_size': 4096
59
+ 'minibatch_size': 1024}
60
  ```
61
 
logs/events.out.tfevents.1677462319.25f188cb86e1.67423.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81549e842b7852e6f10eb479497d0a0decdedba5ebbd77e2ebe35c437ad62bd4
3
+ size 998456
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1646a5c04d2471ad20d041870ca00bed0cf58308ad7583208ea9265ab32c91cd
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:110aa72991bb5f3140765f311382aaaafa21488e163e20879b54c3c1fbf7e240
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": 123.45184778060676, "std_reward": 107.2148313402014, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T01:41:11.260196"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -15.475599507119966, "std_reward": 56.91586458323047, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T01:58:14.736056"}