AGuzhvenko commited on
Commit
b08c70f
·
verified ·
1 Parent(s): f636c04

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: -173.46 +/- 164.88
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': 50000
41
  'learning_rate': 0.00026
42
  'num_envs': 4
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
- 'gamma': 0.98
47
  'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -32.23 +/- 102.88
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': 0.00026
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
logs/events.out.tfevents.1742387753.3eb4472a93c2.14132.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9589a2417cdb79c3492e62e8f69fa2c222eeb0f0426868375e89e798f9067142
3
+ size 380760
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f92de7a1082312320925a07bb4f0bd2e769f65723911d1e75dc50f8518ea9f7d
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28d335bc405f0e8bc821d035c30d5f5bc41d710fbbe466da4762bf1380214d42
3
  size 43026
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a1a4f5b22aa9b60079a3e579db34a7e0483005d709b623a35106ceb555b3771
3
- size 24042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f042ebdb18ed6be3c2aec05352849107e8962948e65b0903bcee13fedaae88
3
+ size 233510
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "LunarLander-v2", "mean_reward": -173.45613973172743, "std_reward": 164.8839267913277, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-19T12:35:01.303700"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -32.23069269429324, "std_reward": 102.88218608543096, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-19T12:41:56.994633"}