Information Gathering in Decentralized POMDPs by Policy Graph Improvement.
Mikko LauriJoni PajarinenJan PetersPublished in: CoRR (2019)
Keyphrases
- information gathering
- dec pomdps
- partially observable markov decision processes
- resource bounded
- decision process
- optimal policy
- information fusion
- partially observable
- distributed constraint optimization
- infinite horizon
- markov decision problems
- policy gradient
- policy search
- random walk
- reinforcement learning
- markov decision processes
- point based value iteration
- decision making
- multi agent
- dynamical systems
- control policies
- continuous state
- distributed systems
- peer to peer
- weighted graph
- belief state
- dynamic programming
- finite state
- linear programming
- decision makers
- decision problems
- decision support system
- markov chain
- information technology