Aubins commited on
Commit
f8acd4f
·
verified ·
1 Parent(s): ad6f829

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: -87.88 +/- 56.29
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -39,7 +39,7 @@ model-index:
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 100000
41
  'learning_rate': 0.0003
42
- 'num_envs': 8
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Aubins/CustomPPO-LunarLander-v2'
58
- 'batch_size': 1024
59
- 'minibatch_size': 256}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -4.27 +/- 69.64
21
  name: mean_reward
22
  verified: false
23
  ---
 
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 100000
41
  'learning_rate': 0.0003
42
+ 'num_envs': 4
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Aubins/CustomPPO-LunarLander-v2'
58
+ 'batch_size': 512
59
+ 'minibatch_size': 128}
60
  ```
61
 
logs/events.out.tfevents.1760012099.cfc0f405fae3.640.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0f0287d6f3b4733115ca7b3a1783ccf481ac09a1bc1a3d335e7e767b705dc51
3
+ size 169394
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:537d49ddd47f9c12b3c90e60c62d6762792736b0d70833a96ad23b7eee19284b
3
  size 276266
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96058f17c49b17f2550d891eea73314c7afd773c11ed0b563db039a88141be6d
3
  size 276266
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b97e4a468cf2665afdbc164b244aa48ddca950c6d33ff6ae002e9cb288c59e37
3
- size 27033
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bb8c45bfbf849e0ba4850128d1aaab5f66f5f77b0a2da8c8defeb5ee4d185f8
3
+ size 35063
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "LunarLander-v2", "mean_reward": -87.88102218136405, "std_reward": 56.29471624184207, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-09T12:13:40.657610"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -4.2729909308931155, "std_reward": 69.64013365582284, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-09T12:16:52.716652"}