Push agent to the Hub
Browse files- README.md +7 -7
- logs/events.out.tfevents.1733253619.8835d05a856b.61846.0 +3 -0
- model.pt +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
|
@@ -17,7 +17,7 @@ model-index:
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
-
value:
|
| 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':
|
| 41 |
'learning_rate': 0.00025
|
| 42 |
-
'num_envs':
|
| 43 |
-
'num_steps':
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
'gamma': 0.99
|
| 47 |
'gae_lambda': 0.95
|
| 48 |
'num_minibatches': 4
|
| 49 |
-
'update_epochs':
|
| 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': 'ahmadsy/ppo_scratch-LunarLander-v2'
|
| 58 |
-
'batch_size':
|
| 59 |
-
'minibatch_size':
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: 281.26 +/- 46.16
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
+
'total_timesteps': 1000000
|
| 41 |
'learning_rate': 0.00025
|
| 42 |
+
'num_envs': 32
|
| 43 |
+
'num_steps': 64
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
'gamma': 0.99
|
| 47 |
'gae_lambda': 0.95
|
| 48 |
'num_minibatches': 4
|
| 49 |
+
'update_epochs': 32
|
| 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': 'ahmadsy/ppo_scratch-LunarLander-v2'
|
| 58 |
+
'batch_size': 2048
|
| 59 |
+
'minibatch_size': 512}
|
| 60 |
```
|
| 61 |
|
logs/events.out.tfevents.1733253619.8835d05a856b.61846.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:576c8d86fe659303a46c70ffabb7a90283906749674a8ae6b659a374ed255837
|
| 3 |
+
size 734991
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 59774
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47e123978f6c5300815a50ff9b72c6af29c8bb9b0e968bfbba726d0abacd1c60
|
| 3 |
size 59774
|
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":
|
|
|
|
| 1 |
+
{"env_id": "LunarLander-v2", "mean_reward": 281.25645566888534, "std_reward": 46.16207389460132, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-03T19:38:27.060109"}
|