10 citations · 28 across the 9 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023★ 1 cited
Towards Learning Rubik's Cube with N-tuple-based Reinforcement Learning
Wolfgang Konen
This work describes in detail how to learn and solve the Rubik's cube game (or puzzle) in the General Board Game (GBG) learning and playing framework. We cover the cube sizes 2x2x2…
cs.LG2022★ 10 cited
AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time
Johannes Scheiermann, Wolfgang Konen
Recently, the seminal algorithms AlphaGo and AlphaZero have started a new era in game learning and deep reinforcement learning. While the achievements of AlphaGo and AlphaZero - pl…