GerardMR commited on
Commit
d61cdec
1 Parent(s): 19c52d6

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: -34.79 +/- 76.74
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,7 +37,7 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 200000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
  'num_steps': 128
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -45.36 +/- 17.39
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 500000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
  'num_steps': 128
logs/events.out.tfevents.1701460554.5051f8bd6bde.9698.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06bf416388122dc0c9a199f9afb72914f1725d442c009b7374f0436640ec14d1
3
+ size 673750
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1efdb17a91d165475a33b5df37ed9e8049c65b910cf084fd420eda94a1e63838
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f77ef9c75a6010d53b638b2fbf6a0a2a078997ab1d6d29a1b7ff740ac1d0c4bf
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": -34.789524030356475, "std_reward": 76.74266899813878, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-01T19:53:55.993333"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -45.36257709680734, "std_reward": 17.38747178196027, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-01T20:10:23.104919"}