pittawat commited on
Commit
513337c
1 Parent(s): 7a6febb

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: -140.46 +/- 90.33
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -48,12 +48,12 @@ model-index:
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
51
- 'clip_coef': 0.2
52
  'clip_vloss': True
53
  'ent_coef': 0.01
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
- 'target_kl': None
57
  'repo_id': 'pittawat/LunarLander-v2-ppo'
58
  'batch_size': 512
59
  'minibatch_size': 128}
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -111.40 +/- 50.72
21
  name: mean_reward
22
  verified: false
23
  ---
 
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
51
+ 'clip_coef': 0.5
52
  'clip_vloss': True
53
  'ent_coef': 0.01
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
+ 'target_kl': 0.3
57
  'repo_id': 'pittawat/LunarLander-v2-ppo'
58
  'batch_size': 512
59
  'minibatch_size': 128}
logs/events.out.tfevents.1676509806.f39059416aa0.6742.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2b2f58cb59c1de660f0f9528198e6183d6bddefcf99a133cae1b4f1962d2979
3
+ size 105960
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93fcdcfc67e1d3b963a2bb12709861aaaa4b9354d5eeaa796693038c7a45cb56
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": -140.45658990684834, "std_reward": 90.33446661106434, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T01:08:18.875202"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -111.39584349237634, "std_reward": 50.716599164926464, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T01:10:51.756274"}