Bandit Submodular Maximization for Multi-Robot Coordination in Unpredictable and Partially Observable Environments.
Zirui XuXiaofeng LinVasileios TzoumasPublished in: Robotics: Science and Systems (2023)
Keyphrases
- partially observable environments
- multi robot coordination
- objective function
- multi robot
- inverse reinforcement learning
- partially observable
- reinforcement learning algorithms
- reinforcement learning
- path planning
- cooperative games
- mobile robot
- markov chain
- partially observable markov decision processes
- probability distribution
- vision system
- monte carlo
- markov decision processes
- finite state