Deep Reinforcement Learning for Decentralized Multi-Robot Exploration with Macro Actions.
Aaron Hao TanFederico Pizarro BejaranoGoldie NejatPublished in: CoRR (2021)
Keyphrases
- macro actions
- reinforcement learning
- multi robot exploration
- multi robot
- markov decision processes
- multi agent
- state space
- optimal policy
- reinforcement learning algorithms
- function approximation
- multiple robots
- dynamic programming
- partially observable
- model free
- learning algorithm
- path planning
- continuous state
- learned knowledge
- planning domains
- markov decision process
- intelligent agents
- dynamic environments