mgmeskill commited on
Commit
2b6861d
·
1 Parent(s): 95bdfac

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: -33.47 +/- 103.65
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -38,16 +38,16 @@ model-index:
38
  'capture_video': False
39
  'f': '/root/.local/share/jupyter/runtime/kernel-034b7df4-145b-4db4-9d09-b6d875ced33d.json'
40
  'env_id': 'LunarLander-v2'
41
- 'total_timesteps': 100000
42
  'learning_rate': 0.001
43
  'num_envs': 4
44
  'num_steps': 128
45
  'anneal_lr': True
46
  'gae': True
47
  'gamma': 0.99
48
- 'gae_lambda': 0.8
49
  'num_minibatches': 4
50
- 'update_epochs': 2
51
  'norm_adv': True
52
  'clip_coef': 0.2
53
  'clip_vloss': True
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 75.67 +/- 130.43
21
  name: mean_reward
22
  verified: false
23
  ---
 
38
  'capture_video': False
39
  'f': '/root/.local/share/jupyter/runtime/kernel-034b7df4-145b-4db4-9d09-b6d875ced33d.json'
40
  'env_id': 'LunarLander-v2'
41
+ 'total_timesteps': 1000000
42
  'learning_rate': 0.001
43
  'num_envs': 4
44
  'num_steps': 128
45
  'anneal_lr': True
46
  'gae': True
47
  'gamma': 0.99
48
+ 'gae_lambda': 0.88
49
  'num_minibatches': 4
50
+ 'update_epochs': 3
51
  'norm_adv': True
52
  'clip_coef': 0.2
53
  'clip_vloss': True
logs/events.out.tfevents.1691896235.4c5d58e91a6c.225.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19095757586668523343414a76a084c3fda93aeee21dd23a3a2191937f7f33cf
3
+ size 1222589
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8dacc41dfb18aca3bc40ab6b16d5cd2e61ac8b6c6e19ce7e0332153a3e7c66d
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7318ca5d8ba02dd302edbdd734254608492fb3f0e1e02927343fd2c9a0a1dca9
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": -33.47175804657828, "std_reward": 103.64850620213647, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T03:09:26.683247"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 75.66851044080843, "std_reward": 130.43451595374478, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T03:42:52.455396"}