Push agent to the Hub
Browse files- README.md +9 -9
- logs/events.out.tfevents.1722595821.LAPTOP-1P7DPSC7.38572.0 +3 -0
- model.pt +2 -2
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
-
-
|
| 4 |
- ppo
|
| 5 |
- deep-reinforcement-learning
|
| 6 |
- reinforcement-learning
|
|
@@ -13,18 +13,18 @@ model-index:
|
|
| 13 |
type: reinforcement-learning
|
| 14 |
name: reinforcement-learning
|
| 15 |
dataset:
|
| 16 |
-
name:
|
| 17 |
-
type:
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
-
value:
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
| 24 |
|
| 25 |
-
# PPO Agent Playing
|
| 26 |
|
| 27 |
-
This is a trained model of a PPO agent playing
|
| 28 |
|
| 29 |
# Hyperparameters
|
| 30 |
```python
|
|
@@ -36,8 +36,8 @@ model-index:
|
|
| 36 |
'wandb_project_name': 'cleanRL'
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
-
'env_id': '
|
| 40 |
-
'total_timesteps':
|
| 41 |
'learning_rate': 0.00025
|
| 42 |
'num_envs': 4
|
| 43 |
'num_steps': 128
|
|
@@ -54,7 +54,7 @@ model-index:
|
|
| 54 |
'vf_coef': 0.5
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
'target_kl': None
|
| 57 |
-
'repo_id': 'bakermann/ppo-
|
| 58 |
'batch_size': 512
|
| 59 |
'minibatch_size': 128}
|
| 60 |
```
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
+
- LunarLander-v2
|
| 4 |
- ppo
|
| 5 |
- deep-reinforcement-learning
|
| 6 |
- reinforcement-learning
|
|
|
|
| 13 |
type: reinforcement-learning
|
| 14 |
name: reinforcement-learning
|
| 15 |
dataset:
|
| 16 |
+
name: LunarLander-v2
|
| 17 |
+
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -166.08 +/- 99.21
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
| 24 |
|
| 25 |
+
# PPO Agent Playing LunarLander-v2
|
| 26 |
|
| 27 |
+
This is a trained model of a PPO agent playing LunarLander-v2.
|
| 28 |
|
| 29 |
# Hyperparameters
|
| 30 |
```python
|
|
|
|
| 36 |
'wandb_project_name': 'cleanRL'
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
+
'env_id': 'LunarLander-v2'
|
| 40 |
+
'total_timesteps': 50
|
| 41 |
'learning_rate': 0.00025
|
| 42 |
'num_envs': 4
|
| 43 |
'num_steps': 128
|
|
|
|
| 54 |
'vf_coef': 0.5
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
'target_kl': None
|
| 57 |
+
'repo_id': 'bakermann/ppo-LunarLander-v2'
|
| 58 |
'batch_size': 512
|
| 59 |
'minibatch_size': 128}
|
| 60 |
```
|
logs/events.out.tfevents.1722595821.LAPTOP-1P7DPSC7.38572.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76210479ecb94f393b5c042adede06c5ad891b82d7fa6260c3f478f04e3fd11a
|
| 3 |
+
size 737
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c76d2260978248593cfa7e82b9937ae6b9da3048967387d6e2136719b874dde9
|
| 3 |
+
size 42898
|
replay.mp4
CHANGED
|
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"env_id": "
|
|
|
|
| 1 |
+
{"env_id": "LunarLander-v2", "mean_reward": -166.0772420793574, "std_reward": 99.21451115055338, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-02T12:50:24.210236"}
|