Showing cs.AIShow all
2 papers · 1 filter
cs.AI2020
Neural Game Engine: Accurate learning of generalizable forward models from pixels
Chris Bamford, Simon Lucas
Access to a fast and easily copied forward model of a game is essential for model-based reinforcement learning and for algorithms such as Monte Carlo tree search, and is also benef…
cs.AI2019
A Local Approach to Forward Model Learning: Results on the Game of Life Game
Simon M. Lucas, Alexander Dockhorn, Vanessa Volz +6
This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent. We transform Conway's Game of Life simulation into a sing…