Anticipating Oblivious Opponents in Stochastic Games

TL;DR

This paper introduces a method to predict the actions of oblivious environments in stochastic games by synthesizing an information state machine, enabling optimal policy computation to maximize rewards in various scenarios.

Contribution

It presents a novel approach for systematically anticipating oblivious environment policies using an information state machine with consistency guarantees.

Findings

Successfully anticipates environment policies in benchmark tasks

Maximizes reward in human activity scenarios

Provides a method for checking automaton consistency

Abstract

We present an approach for systematically anticipating the actions and policies employed by \emph{oblivious} environments in concurrent stochastic games, while maximizing a reward function. Our main contribution lies in the synthesis of a finite \emph{information state machine} whose alphabet ranges over the actions of the environment. Each state of the automaton is mapped to a belief state about the policy used by the environment. We introduce a notion of consistency that guarantees that the belief states tracked by our automaton stays within a fixed distance of the precise belief state obtained by knowledge of the full history. We provide methods for checking consistency of an automaton and a synthesis approach which upon successful termination yields such a machine. We show how the information state machine yields an MDP that serves as the starting point for computing optimal policies for maximizing a reward function defined over plays. We present an experimental evaluation over benchmark examples including human activity data for tasks such as cataract surgery and furniture assembly, wherein our approach successfully anticipates the policies and actions of the environment in order to maximize the reward.