A Framework for Sequential Planning in Multi-Agent Settings
| Autor: | Piotr J. Gmytrasiewicz, Prashant Doshi |
|---|---|
| Rok vydání: | 2005 |
| Předmět: |
FOS: Computer and information sciences
0209 industrial biotechnology Mathematical optimization Computer Science - Artificial Intelligence Computer science Process (engineering) Bayesian probability Observable 02 engineering and technology Computer Science::Multiagent Systems symbols.namesake Artificial Intelligence (cs.AI) 020901 industrial engineering & automation Artificial Intelligence Nash equilibrium Complete information 0202 electrical engineering electronic engineering information engineering symbols State space Computer Science - Multiagent Systems 020201 artificial intelligence & image processing Markov decision process Multiagent Systems (cs.MA) |
| Zdroj: | Journal of Artificial Intelligence Research. 24:49-79 |
| ISSN: | 1076-9757 |
| Popis: | 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 agent's 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|