This paper describes a Relevance-Zone pattern table (RZT) that can be us...
Goal-achieving problems are puzzles that set up a specific situation wit...
Sim-to-real, a term that describes where a model is trained in a simulat...
AlphaZero has been very successful in many games. Unfortunately, it stil...
Many of the strongest game playing programs use a combination of Monte C...
In this paper, we point out a fundamental property of the objective in
r...
This paper proposes a new approach to a novel value network architecture...
The Google DeepMind challenge match in March 2016 was a historic achieve...