bwalser commited on
Commit
507c0fc
·
verified ·
1 Parent(s): 8482278

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: -154.94 +/- 106.76
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,10 +37,10 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': True
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 50000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
- 'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'bwalser/lunarlander-ppo-v2'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -145.06 +/- 100.56
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': True
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 100000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
+ 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'bwalser/lunarlander-ppo-v2'
58
+ 'batch_size': 4096
59
+ 'minibatch_size': 1024}
60
  ```
61
 
logs/events.out.tfevents.1724931198.bw-general-new.95323.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e83fbfa13ad3cb67f63ff37baf3a4b8e97aa150753c0d6b4327df56dc91ef520
3
+ size 138701
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55cfc412ddc3da35898630aaec5f68a300592fbb5358e70da9b6eaed531249dc
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4031c896fc22ed61ffa3b291ea4069761cb5eb31f6064b706bfc1bc8f5a51abe
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": -154.9378148218738, "std_reward": 106.7631467660152, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-29T11:24:03.377439"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -145.06265534308756, "std_reward": 100.56158877296807, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-29T11:34:25.537450"}