UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Learning to design games: Strategic environments in reinforcement learning

Zhang, H; Wang, J; Zhou, Z; Zhang, W; Wen, Y; Yu, Y; Li, W; (2018) Learning to design games: Strategic environments in reinforcement learning. In: (pp. pp. 3068-3074). ArXiv Green open access

[thumbnail of 1707.01310.pdf]
Preview
Text
1707.01310.pdf - Accepted Version

Download (2MB) | Preview

Abstract

In typical reinforcement learning (RL), the environment is assumed given and the goal of the learning is to identify an optimal policy for the agent taking actions through its interactions with the environment. In this paper, we extend this setting by considering the environment is not given, but controllable and learnable through its interaction with the agent at the same time. This extension is motivated by environment design scenarios in the real-world, including game design, shopping space design and traffic signal design. Theoretically, we find a dual Markov decision process (MDP) w.r.t. the environment to that w.r.t. the agent, and derive a policy gradient solution to optimizing the parametrized environment. Furthermore, discontinuous environments are addressed by a proposed general generative framework. Our experiments on a Maze game design task show the effectiveness of the proposed algorithms in generating diverse and challenging Mazes against various agent settings.

Type: Proceedings paper
Title: Learning to design games: Strategic environments in reinforcement learning
ISBN-13: 9780999241127
Open access status: An open access version is available from UCL Discovery
Publisher version: https://arxiv.org/abs/1707.01310
Language: English
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > UCL School of Management
URI: https://discovery.ucl.ac.uk/id/eprint/10066099
Downloads since deposit
86Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item