anders0204 commited on
Commit
4a7bd7a
·
1 Parent(s): af9fe1e

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: -161.21 +/- 74.41
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -39,9 +39,9 @@ model-index:
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 1000000
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': 0.98
@@ -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': 2048
59
- 'minibatch_size': 256}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -387.14 +/- 261.85
21
  name: mean_reward
22
  verified: false
23
  ---
 
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 1000000
41
  'learning_rate': 0.0003
42
+ 'num_envs': 4
43
  'num_steps': 128
44
+ 'anneal_lr': False
45
  'gae': True
46
  'gamma': 0.999
47
  'gae_lambda': 0.98
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'anders0204/ppo-LunarLander-v2'
58
+ 'batch_size': 512
59
+ 'minibatch_size': 64}
60
  ```
61
 
logs/events.out.tfevents.1696844913.Anderss-MacBook-Pro-4.local.51844.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a9effbf2e68ca77a0321a44e9d3fb52d6111e925694bc192f40e1c2ac2a9963
3
+ size 2376842
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e17d0ac716366d72d1c7a2277dfd28184d9361dc1f68ef9f1ad10dd4d9d0611a
3
  size 42469
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42f8354c81628240c3aaedad1977468e5bb4d6ef5cc254820d91b9641db50e01
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": -161.21349885020265, "std_reward": 74.41304049564212, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-09T11:44:14.471041"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -387.14324511114205, "std_reward": 261.85264646584864, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-09T13:12:32.364266"}