fermaat commited on
Commit
bf0fe59
1 Parent(s): c135b89

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: -133.00 +/- 43.72
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,15 +37,15 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 50000
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
51
  'clip_coef': 0.2
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'fermaat/ppo-LunarLander-scratch'
58
- 'batch_size': 4096
59
- 'minibatch_size': 1024}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -14.30 +/- 118.45
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 500000
41
  'learning_rate': 0.00025
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': 16
49
  'update_epochs': 4
50
  'norm_adv': True
51
  'clip_coef': 0.2
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'fermaat/ppo-LunarLander-scratch'
58
+ 'batch_size': 512
59
+ 'minibatch_size': 32}
60
  ```
61
 
logs/events.out.tfevents.1677177468.a4105b5668f5.13632.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28d0cd8eb98509f977f6f88fdb437b09178dddf90b2b4d920e6c5c5ed938688d
3
+ size 631499
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7bf2974f5cc193d99e5328c0f2d9c86597a90829095c0b455e6761a4d4622e4
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:654525486d95e217230ea42d3da0627dd8db78a65329581a2953711a8d8a8c67
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": -133.0039144719493, "std_reward": 43.722645667676446, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-23T18:15:18.457383"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -14.302093163783747, "std_reward": 118.44641372830634, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-23T18:54:50.076481"}