SuperDan commited on
Commit
1ec3695
1 Parent(s): f5cd736

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: -213.42 +/- 111.62
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -31,22 +31,22 @@ model-index:
31
  {'exp_name': 'ppo'
32
  'gym_id': 'LunarLander-v2'
33
  'env_id': 'LunarLander-v2'
34
- 'learning_rate': 0.00025
35
  'seed': 1
36
- 'total_timesteps': 300000
37
  'torch_deterministic': True
38
  'cuda': True
39
  'track': False
40
  'wandb_project_name': 'ppo-implementation-details'
41
  'wandb_entity': None
42
  'capture_video': False
43
- 'num_envs': 2048
44
- 'num_steps': 1024
45
  'anneal_lr': True
46
  'gae': True
47
  'gamma': 0.99
48
  'gae_lambda': 0.95
49
- 'num_minibatches': 256
50
  'update_epochs': 4
51
  'norm_adv': True
52
  'clip_coef': 0.2
@@ -56,7 +56,7 @@ model-index:
56
  'max_grad_norm': 0.5
57
  'target_kl': None
58
  'repo_id': 'SuperDan/ppo-lunar-sharedMLP'
59
- 'batch_size': 2097152
60
- 'minibatch_size': 8192}
61
  ```
62
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 109.93 +/- 52.00
21
  name: mean_reward
22
  verified: false
23
  ---
 
31
  {'exp_name': 'ppo'
32
  'gym_id': 'LunarLander-v2'
33
  'env_id': 'LunarLander-v2'
34
+ 'learning_rate': 0.0005
35
  'seed': 1
36
+ 'total_timesteps': 8388608
37
  'torch_deterministic': True
38
  'cuda': True
39
  'track': False
40
  'wandb_project_name': 'ppo-implementation-details'
41
  'wandb_entity': None
42
  'capture_video': False
43
+ 'num_envs': 1024
44
+ 'num_steps': 256
45
  'anneal_lr': True
46
  'gae': True
47
  'gamma': 0.99
48
  'gae_lambda': 0.95
49
+ 'num_minibatches': 128
50
  'update_epochs': 4
51
  'norm_adv': True
52
  'clip_coef': 0.2
 
56
  'max_grad_norm': 0.5
57
  'target_kl': None
58
  'repo_id': 'SuperDan/ppo-lunar-sharedMLP'
59
+ 'batch_size': 262144
60
+ 'minibatch_size': 2048}
61
  ```
62
 
logs/events.out.tfevents.1702250145.f982b9416d82.5070.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d4d97f0d8ca4096182f25d4122b28bc8d9bc931bf97c4e9e1b1bc223dd29e52
3
+ size 727144
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88bcc5467c57ead0a38a64f0e057789b675891fc492cc2e68c6ecef2ffda2ce3
3
  size 1082216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40d201d030a60ab8ae09d329af2b5ebb6ac7a096fea6f4915323169fa7b59d1
3
  size 1082216
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": -213.41949862860216, "std_reward": 111.62084535750283, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-10T02:36:43.727016"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 109.9289331221125, "std_reward": 51.99909361399946, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-11T02:10:12.815904"}