search

Kautenja / gym-super-mario-bros

An OpenAI Gym interface to Super Mario Bros. & Super Mario Bros. 2 (Lost Levels) on The NES
Other
685 stars 134 forks source link

Supporting custom state representations #82

Closed cdvv7788 closed 5 years ago

cdvv7788 commented 5 years ago

Is your feature request related to a problem? Please describe.

The current state representations is nice if you want to work with the whole image. If you want to try something simple, like Q-learning, the state representation needs to change.

Describe the solution you'd like

I would like to have a way to encode the state into something different than the current image (http://cs229.stanford.edu/proj2012/LiaoYiYang-RLtoPlayMario.pdf)

Describe alternatives you've considered

If all the necessary information could be encoded in the info field, that information could be used to encode the state instead of the raw state provided, without affecting the current API.

Kautenja commented 5 years ago

What I believe you're describing is manual feature engineering at the game logic level. While a totally valid technique, it is not a primary objective of this project which aims to be a simple model of human interaction with the game. However, feel free to create a fork! This idea has been explored by @ppaquette and is also referred to in #85.