Point-Based Bounded Policy Iteration for Decentralized POMDPs.
Youngwook KimKee-Eung KimPublished in: PRICAI (2010)
Keyphrases
- policy iteration
- markov decision processes
- dec pomdps
- infinite horizon
- reinforcement learning
- point based value iteration
- policy iteration algorithm
- markov decision problems
- optimal policy
- partially observable markov decision processes
- finite state
- sample path
- average reward
- partially observable
- distributed constraint optimization
- model free
- multi agent
- state space
- markov decision process
- planning under uncertainty
- dynamic programming
- policy evaluation
- fixed point
- reinforcement learning algorithms
- temporal difference
- least squares
- continuous state
- actor critic
- linear programming
- optimal control
- belief state
- average cost
- decision theoretic
- action space
- control system
- markov chain
- multistage
- dynamical systems
- reward function