Paper Info
Title
Learning to Design Games: Strategic Environments in Reinforcement Learning.
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. Theoretically, we find a dual Markov decision process (MDP) w.r.t. the environment to that w.r.t. the agent, and solving the dual MDP-policy pair yields a policy gradient solution to optimizing the parametrized environment. Furthermore, environments with discontinuous parameters are addressed by a proposed general generative framework. While the idea is illustrated by an extended two-agent rock-paper-scissors game, our experiments on a Maze game design task show the effectiveness of the proposed algorithm in generating diverse and challenging Mazes against different agents with various settings.
Year
DOI
Venue
2018
10.24963/ijcai.2018/426
IJCAI
Field
DocType
Citations 
Computer science,Game design,Markov decision process,Q-learning,Artificial intelligence,Generative grammar,Error-driven learning,Machine learning,Reinforcement learning
Conference
0
PageRank 
References 
Authors
0.34
16
7
Name
Order
Citations
PageRank
Haifeng Zhang121.71
Jun Wang25520.58
Zhiming Zhou3193.66
Weinan Zhang4122897.24
Yin Wen500.68
Yong Yu67637380.66
Wenxin Li742.49