Reinforcement learning in an emulated NES environment

Banzas Illa, Tomás

Reinforcement learning in an emulated NES environment

License

Citation

Banzas Illa, T. Reinforcement learning in an emulated NES environment. 2015. handle: http://hdl.handle.net/10230/25482

This citation was generated automatically.

Abstract

A short review and comparison of Q-Learning, Function Approximation by gradient descent and Monte Carlo Tree Search algorithms, implemented to run on an environment based on an emulation of the Nintendo Entertainment System video gaming console. The Nintendo Entertainment System and its catalogue of games/nprovide a multitude of scenarios to research learning algorithms. Different states and rewards are produced in real-time using memory snapshots provided by an emulator running different games. Although the state space of Nintendo Entertainment System is much larger than that of an Atari, Monte Carlo Tree Search is still able to learn useful/npolicies.