jth5220 commited on
Commit
4bb9d52
·
verified ·
1 Parent(s): a0f64ac

Push agent to the Hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -17,7 +17,7 @@ model-index:
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
- value: -0.07 +/- 107.09
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -43,8 +43,8 @@ model-index:
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
50
  'norm_adv': True
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 87.15 +/- 52.65
21
  name: mean_reward
22
  verified: false
23
  ---
 
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.999
47
+ 'gae_lambda': 0.98
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
logs/events.out.tfevents.1738749675.bb67e88a0492.22661.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30ebc8074de8e581465f1f2c3be66692395c1fb8b3e369746b52c4321b563b28
3
+ size 1303747
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9a2f5da9739cd080252297480009c8939101f5219045009864dcb78b9e2c213
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a6f86f05752ce6a7bf53c4f5c4a663358274bec2cee87a4da1c8f95161ecd2c
3
  size 43026
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": -0.0665043279116361, "std_reward": 107.09108579646897, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-05T09:50:41.244238"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 87.14637992934374, "std_reward": 52.653950589100795, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-05T10:27:04.425212"}