Balanced Map Coverage using Reinforcement Learning in Repeated Obstacle Environments.
Xue XiaThaddeus A. RoppelJohn Y. HungJian ZhangSenthilkumar C. G. PeriaswamyJustin PattonPublished in: ISIE (2020)
Keyphrases
- reinforcement learning
- function approximation
- state space
- multi agent environments
- mobile robot
- optimal policy
- markov decision processes
- artificial intelligence
- dynamic environments
- machine learning
- multi agent
- real world
- learning algorithm
- temporal difference
- reinforcement learning algorithms
- information systems
- dynamic programming
- robotic systems
- multi agent reinforcement learning