A Framework for Sequential Planning in Multi-Agent Settings

TL;DR

This paper extends POMDPs to multi-agent scenarios by incorporating agent models into the state space, enabling belief-based decision making that accounts for other agents' beliefs and types, with convergence properties similar to single-agent POMDPs.

Contribution

It introduces a multi-agent POMDP framework with belief updates over other agents' models, capturing complex interactions while maintaining key properties of traditional POMDPs.

Findings

Belief updates and value functions exhibit properties like convergence and convexity.

Approximate solutions are computable despite the complexity of nested beliefs.

The framework is demonstrated through a simple application domain.

Abstract

This paper extends the framework of partially observable Markov decision processes (POMDPs) to multi-agent settings by incorporating the notion of agent models into the state space. Agents maintain beliefs over physical states of the environment and over models of other agents, and they use Bayesian updates to maintain their beliefs over time. The solutions map belief states to actions. Models of other agents may include their belief states and are related to agent types considered in games of incomplete information. We express the agents autonomy by postulating that their models are not directly manipulable or observable by other agents. We show that important properties of POMDPs, such as convergence of value iteration, the rate of convergence, and piece-wise linearity and convexity of the value functions carry over to our framework. Our approach complements a more traditional approach to interactive settings which uses Nash equilibria as a solution paradigm. We seek to avoid some of the drawbacks of equilibria which may be non-unique and do not capture off-equilibrium behaviors. We do so at the cost of having to represent, process and continuously revise models of other agents. Since the agents beliefs may be arbitrarily nested, the optimal solutions to decision making problems are only asymptotically computable. However, approximate belief updates and approximately optimal plans are computable. We illustrate our framework using a simple application domain, and we show examples of belief updates and value functions.