yumouwei commited on
Commit
dc86381
·
1 Parent(s): 02cd03f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -1,9 +1,9 @@
1
  # super-mario-bros-reinforcement-learning
2
  My implementation of an RL model to play the NES Super Mario Bros using Stable-Baselines3 (SB3). As of today (Aug 14 2022) the trained PPO agent completed World 1-1.
3
 
4
- The pre-trained models are located under ./models. To run these models run ./smb-ram-ppo-play.ipynb.
5
 
6
- To train a new model run ./smb-ram-ppo-train.ipynb.
7
 
8
  ![world-1-1-n_stack=4](https://user-images.githubusercontent.com/46117079/185268710-2d477eb0-b3f7-4ab8-865d-130e3a23a3e9.gif)
9
 
 
1
  # super-mario-bros-reinforcement-learning
2
  My implementation of an RL model to play the NES Super Mario Bros using Stable-Baselines3 (SB3). As of today (Aug 14 2022) the trained PPO agent completed World 1-1.
3
 
4
+ The pre-trained models are located under `./models`. To run these models run `./smb-ram-ppo-play.ipynb`.
5
 
6
+ To train a new model run `./smb-ram-ppo-train.ipynb`.
7
 
8
  ![world-1-1-n_stack=4](https://user-images.githubusercontent.com/46117079/185268710-2d477eb0-b3f7-4ab8-865d-130e3a23a3e9.gif)
9