anders0204 commited on
Commit
6f0c190
·
1 Parent(s): 88d49ed

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: -180.47 +/- 107.52
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -39,11 +39,11 @@ model-index:
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 10000
41
  'learning_rate': 0.0003
42
- 'num_envs': 4
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
- 'gamma': 0.99
47
  'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'anders0204/ppo-LunarLander-v2'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -203.75 +/- 97.83
21
  name: mean_reward
22
  verified: false
23
  ---
 
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 10000
41
  'learning_rate': 0.0003
42
+ 'num_envs': 16
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.999
47
  'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'anders0204/ppo-LunarLander-v2'
58
+ 'batch_size': 2048
59
+ 'minibatch_size': 512}
60
  ```
61
 
logs/events.out.tfevents.1696597662.Anderss-MacBook-Pro-4.local.44004.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4d5b777b6d6246bfbcf25991ac9ecf05be032c36d559ceb034064e7c6bf2c69
3
+ size 11424
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f2604e830a87b89bfff517f6ac63e865636b04038c68a9b123224cb0381b866
3
  size 42469
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f90bbd202e6b70ee8b9637f3df83e4c03d82e2214bbcf8f1938eaa9e634169
3
  size 42469
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": -180.46681500823053, "std_reward": 107.52223098622567, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-06T15:06:21.470371"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -203.75378971827337, "std_reward": 97.83420061827518, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-06T15:07:55.187829"}