Planning, Inference and Pragmatics in Sequential Language Games

by   Fereshte Khani, et al.

We study sequential language games in which two players, each with private information, communicate to achieve a common goal. In such games, a successful player must (i) infer the partner's private information from the partner's messages, (ii) generate messages that are most likely to help with the goal, and (iii) reason pragmatically about the partner's strategy. We propose a model that captures all three characteristics and demonstrate their importance in capturing human behavior on a new goal-oriented dataset we collected using crowdsourcing.


Coalitional Games with Stochastic Characteristic Functions and Private Types

The research on coalitional games has focused on how to share the reward...

Computation of Stackelberg Equilibria of Finite Sequential Games

The Stackelberg equilibrium solution concept describes optimal strategie...

Deviator Detection under Imperfect Monitoring

Grim-trigger strategies are a fundamental mechanism for sustaining equil...

An Incremental Truth Inference Approach to Aggregate Crowdsourcing Contributions in Games with a Purpose

We introduce our approach for incremental truth inference over the contr...

Sequential decomposition of dynamic games with asymmetric information and dependent states

We consider a finite-horizon dynamic game with asymmetric information wi...

A Dataset for StarCraft AI & an Example of Armies Clustering

This paper advocates the exploration of the full state of recorded real-...

Learning Language Games through Interaction

We introduce a new language learning setting relevant to building adapti...