Winning back the CUP for distributed POMDPs: planning over continuous belief spaces.
Pradeep VarakanthamRanjit NairMilind TambeMakoto YokooPublished in: AAMAS (2006)
Keyphrases
- belief state
- belief space
- point based value iteration
- partially observable markov decision processes
- partially observable
- distributed systems
- distributed constraint optimization
- state space
- distributed environment
- multi agent
- partial observability
- reinforcement learning
- motion planning
- cooperative
- planning under uncertainty
- total hip arthroplasty
- discrete data
- stochastic domains
- belief revision
- predictive state representations
- dynamic environments
- finite state
- planning process
- blocks world
- markov decision processes
- multi agent systems
- partially observable markov decision process
- decision theoretic