utyug1 commited on
Commit
acceb0e
1 Parent(s): 2a9f177

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: -84.58 +/- 50.49
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -40,11 +40,11 @@ model-index:
40
  'total_timesteps': 500000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
- 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.999
47
- 'gae_lambda': 0.98
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'utyug1/ppo-LunarLander-v2'
58
- 'batch_size': 4096
59
- 'minibatch_size': 1024}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -13.78 +/- 46.16
21
  name: mean_reward
22
  verified: false
23
  ---
 
40
  'total_timesteps': 500000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
+ 'num_steps': 512
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.999
47
+ 'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'utyug1/ppo-LunarLander-v2'
58
+ 'batch_size': 2048
59
+ 'minibatch_size': 512}
60
  ```
61
 
logs/events.out.tfevents.1680990962.bi-16.prod.env.769347.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc2209ac18d0d33a0aa94f7a385378267aa528b1e1155ab9104f6f5cf1c52570
3
+ size 525843
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a445c885d552a88115453fc2c7799ea5303c3b8e8a718cab64cbccee34f69fdc
3
  size 42817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc3ef03dee47592ef4ec3e22a4dd6a0afb01d098cedccddc5631f7945d6614c
3
  size 42817
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": -84.58338034513018, "std_reward": 50.487896941793046, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-08T21:54:26.929978"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -13.781872383860962, "std_reward": 46.15839622555713, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-08T22:00:54.492751"}