Learning Explainable Representations of Complex Game-playing Strategies
Authors: Abhijeet Krishnan, Colin M. Potts, Arnav Jhala, Harshad Khadilkar, Shirish Karande, Chris Martens
Organizations: Venture IV 420, North Carolina State University, Raleigh, NC 27606 USA · Department of Aerospace Engineering, Indian Institute of Technology Bombay, Powai, Mumbai 400076, Maharashtra, India · Tata Research Development and Design Centre, Pune 411013, Maharashtra, India · Meserve 138 (Boston campus), Khoury College of Computer Sciences, College of Arts, Media and Design, Northeastern University, Boston, MA 02115 USA
As part of learning to play complex games, human players develop develop abstractions for concepts and strategies of gameplay consistent with game rules to improve their performance. These concepts are applied to explain other players' actions, and to inform their own actions in-game. Understanding other players' strategies is a crucial part of such improvement, but requires time and effort. In this paper, we propose a strategy similar to human cognition for training RL agents to synthesize learned strategies and policies as executable procedures based on sequences of gameplay actions. We present methods to automatically learn such programs to play chess and to solve tasks in a grid-based environment. We show that the learned strategies produce effective actions, and can be learned from gameplay data.
Figures & tables
Figure 3 : Divergence histograms for T
Figure 2
Figure 5 : A sample Karel world of size 4×6 . The blue diamond represents a marker. The agent cannot travel through walls.
School of Instrumentation Science and Optoelectronic Engineering, Beijing University of Aeronautics and Astronautics · Tsinghua University · University of Chinese Academy of Sciences +2