Opportunistic Multi-robot Environmental Sampling via Decentralized Markov Decision Processes.
Ayan DuttaO. Patrick KreidlJason M. O'KanePublished in: DARS (2021)
Keyphrases
- markov decision processes
- multi robot
- multi robot systems
- multi robot coordination
- decentralized control
- path planning
- state space
- mobile robot
- finite state
- dynamic programming
- reinforcement learning
- policy iteration
- transition matrices
- optimal policy
- multi robot exploration
- multiple robots
- average cost
- model based reinforcement learning
- reinforcement learning algorithms
- reachability analysis
- decision theoretic planning
- multi robot cooperative
- planning under uncertainty
- average reward
- action space
- markov decision process
- partially observable
- robotic systems
- monte carlo
- infinite horizon
- robot teams
- cooperative
- reward function
- path finding
- action sets