caioiglesias commited on
Commit
cc42737
1 Parent(s): 8eacbb4

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: -709.43 +/- 139.28
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,8 +37,8 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 30000
41
- 'learning_rate': 0.1
42
  'num_envs': 4
43
  'num_steps': 128
44
  'anneal_lr': True
@@ -46,9 +46,9 @@ model-index:
46
  'gamma': 0.99
47
  'gae_lambda': 0.95
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
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -190.51 +/- 113.62
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 10000
41
+ 'learning_rate': 0.00025
42
  'num_envs': 4
43
  'num_steps': 128
44
  'anneal_lr': True
 
46
  'gamma': 0.99
47
  'gae_lambda': 0.95
48
  'num_minibatches': 4
49
+ 'update_epochs': 10
50
  'norm_adv': True
51
+ 'clip_coef': 0.2
52
  'clip_vloss': True
53
  'ent_coef': 0.01
54
  'vf_coef': 0.5
logs/events.out.tfevents.1677780239.6c4e5c51f044.14981.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38aba88996818ca32aecaddc3372a6404e26c1de36237d51f103abab5834bab7
3
+ size 22014
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:704398968db918249b4295403021dd349901e7e04c70e6332b99460481c18520
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:823a38f775c24b2b307e4e9aa0ec073d45b1d88e352413b7e297b876802741b2
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": -709.4293138816666, "std_reward": 139.2791205573606, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T17:51:58.779860"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -190.50908660906245, "std_reward": 113.6154833434169, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T18:04:14.896089"}