Decentralized Markov Decision Processes for Handling Temporal and Resource constraints in a Multiple Robot System.
Aurélie BeynierAbdel-Illah MouaddibPublished in: DARS (2004)
Keyphrases
- markov decision processes
- resource constraints
- temporal constraints
- optimal policy
- finite state
- transition matrices
- state space
- reinforcement learning
- decentralized control
- policy iteration
- dynamic programming
- mobile robot
- model based reinforcement learning
- average reward
- temporal reasoning
- temporal information
- routing problem
- infinite horizon
- partially observable
- decision theoretic planning
- action space
- markov decision process
- average cost
- reward function
- planning under uncertainty
- markov chain
- multi agent
- linear programming