Reinforcement Learning
Transformers
TensorBoard
LunarLander-v2
ppo
deep-reinforcement-learning
custom-implementation
deep-rl-course
Eval Results (legacy)
Instructions to use kchen621/ppo-LunarLander-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kchen621/ppo-LunarLander-v2 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("kchen621/ppo-LunarLander-v2", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Push agent to the Hub
Browse files- README.md +1 -1
- logs/events.out.tfevents.1687684382.ed9b1e4ee0b4.7008.0 +3 -0
- 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 |
---
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -169.25 +/- 80.22
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
logs/events.out.tfevents.1687684382.ed9b1e4ee0b4.7008.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cc02db5b4f9a52aea09dfc88b7903132429bb8a0d004ab03aa8e721d6fb76a6
|
| 3 |
+
size 109725
|
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": -169.2451845010881, "std_reward": 80.21617245267832, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-25T09:13:54.067948"}
|