A heuristic approach for solving decentralized-POMDP: assessment on the pursuit problem.
Iadine ChadesBruno ScherrerFrançois CharpilletPublished in: SAC (2002)
Keyphrases
- dec pomdps
- dynamic programming
- sequential decision making problems
- combinatorial optimization
- multi agent
- timetabling problem
- markov decision problems
- reinforcement learning
- simulated annealing
- distributed systems
- finding an optimal solution
- branch and bound search
- finite state
- variable ordering
- dynamical systems
- state space
- cooperative
- decision theoretic
- stochastic local search
- markov decision process
- markov decision processes
- optimal solution
- partially observable markov decision processes
- partially observable
- search heuristics
- infinite horizon
- planning problems
- tabu search
- optimal policy
- decision theoretic planning
- peer to peer
- model free reinforcement learning