Deep Reinforcement Learning for Decentralized Multi-Robot Exploration With Macro Actions.
Aaron Hao TanFederico Pizarro BejaranoYuhan ZhuRichard RenGoldie NejatPublished in: IEEE Robotics Autom. Lett. (2023)
Keyphrases
- macro actions
- reinforcement learning
- multi robot exploration
- multi robot
- multi agent
- markov decision processes
- state space
- function approximation
- multiple robots
- learning algorithm
- optimal policy
- reinforcement learning algorithms
- model free
- machine learning
- optimal control
- temporal difference
- partially observable
- policy iteration
- multi agent systems
- dynamic programming
- evolutionary algorithm
- reinforcement learning methods
- artificial neural networks
- continuous state