kinkpunk commited on
Commit
78fc76e
1 Parent(s): e13ea05

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: -18.53 +/- 54.84
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,10 +37,10 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 120000
41
  'learning_rate': 0.0003
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': 'kinkpunk/PPO-LunarLander'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 11.44 +/- 93.21
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 150000
41
  'learning_rate': 0.0003
42
  'num_envs': 4
43
+ 'num_steps': 64
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'kinkpunk/PPO-LunarLander'
58
+ 'batch_size': 256
59
+ 'minibatch_size': 64}
60
  ```
61
 
logs/events.out.tfevents.1676834534.e00ba7557307.18489.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35aa5012741552035f796768dd99c5153fd26b85b0ef33e6b01823e4e01dba9
3
+ size 371649
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddb3044ac0faa1763fff137efa9d3d725ebb7fbe9292747afe1df734b39af82d
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72b58af7b8bbf5e81e649db772900adbef53af434715c53c796e24fedc43743
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": -18.53090300466866, "std_reward": 54.836841387166245, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-18T23:18:33.433704"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 11.436329661688188, "std_reward": 93.20511106271981, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T19:26:09.257346"}