jrad98 commited on
Commit
b35eac3
1 Parent(s): 97ada16

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: -158.25 +/- 82.75
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,16 +37,16 @@ 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': 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
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'jrad98/lunar_lander_v2_unit8_part1'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 91.39 +/- 130.51
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 150000
41
+ 'learning_rate': 0.0005
42
+ 'num_envs': 10
43
+ 'num_steps': 20
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
  'gae_lambda': 0.95
48
+ 'num_minibatches': 10
49
+ 'update_epochs': 20
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'jrad98/lunar_lander_v2_unit8_part1'
58
+ 'batch_size': 200
59
+ 'minibatch_size': 20}
60
  ```
61
 
logs/events.out.tfevents.1700615922.ebdfe1e9c633.15547.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ffb74050aab9d4e65f4626a97909455bc4f8b7f50eadd1f107a42a72e30e77
3
+ size 459806
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82cc0371ad39a908c8394641c1df49c3db759c3f1d680f565286f74a15bab16d
3
  size 43026
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": -158.24960183156216, "std_reward": 82.75372907293468, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-22T01:16:05.480451"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 91.39198588206543, "std_reward": 130.50883287904452, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-22T01:32:50.717504"}