A general approach to environment design with one agent

Authors:
Haoqi Zhang;Yiling Chen;David Parkes
Affiliations:
School of Engineering and Applied Sciences, Harvard University, Cambridge, MA;School of Engineering and Applied Sciences, Harvard University, Cambridge, MA;School of Engineering and Applied Sciences, Harvard University, Cambridge, MA
Venue:
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Year:
2009

Citing 5
Cited 7

Inverse Optimization

Operations Research
k-Implementation

Proceedings of the 4th ACM conference on Electronic commerce
Solving convex programs by random walks

Journal of the ACM (JACM)
Policy teaching through reward function learning

Proceedings of the 10th ACM conference on Electronic commerce
Value-based policy teaching with active indirect elicitation

AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 1

Policy teaching through reward function learning

Proceedings of the 10th ACM conference on Electronic commerce
Toward automatic task design: a progress report

Proceedings of the ACM SIGKDD Workshop on Human Computation
To teach or not to teach?: decision making under uncertainty in ad hoc teams

Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Cultivating desired behaviour: policy teaching via environment-dynamics tweaks

Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Incentive design for adaptive agents

The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
Multiagent environment design in human computation

The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 3
Teaching and leading an ad hoc teammate: Collaboration without pre-coordination

Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

The problem of environment design considers a setting in which an interested party aims to influence an agent's decisions by making limited changes to the agent's environment. Zhang and Parkes [2008] first introduced the environment design concept for a specific problem in the Markov Decision Process setting. In this paper, we present a general framework for the formulation and solution of environment design problems with one agent. We consider both the case in which the agent's local decision model is known and partially unknown to the interested party, and illustrate the framework and results on a linear programming setting. For the latter problem, we formulate an active, indirect elicitation method and provide conditions for convergence and logarithmic convergence. We relate to the problem of inverse optimization and also offer a game-theoretic interpretation of our methods.