Multiagent Planning with Trembling-Hand Perfect Equilibrium in Multiagent POMDPs.
Yuichi YabuMakoto YokooAtsushi IwasakiPublished in: PRIMA (2007)
Keyphrases
- multiagent planning
- dec pomdps
- multi agent
- multiagent systems
- dynamic programming
- single agent
- infinite horizon
- decision theoretic
- continuous state
- theoretical justification
- partially observable markov decision processes
- planning under uncertainty
- optimal plans
- decision making under uncertainty
- efficient computation
- optimal policy
- reinforcement learning
- cooperative
- finite state
- multiple agents
- multi agent systems
- decision makers
- markov decision processes
- game theory
- nash equilibrium
- partially observable
- path finding
- optimal control
- expected utility
- planning problems
- belief state
- search space
- autonomous agents
- state space
- distributed constraint optimization
- decision making