Least-Restrictive Multi-agent Collision Avoidance via Deep Meta Reinforcement Learning and Optimal Control.
Salar AsayeshMo ChenMehran MehrandezhKamal GuptaPublished in: RiTA (2022)
Keyphrases
- optimal control
- collision avoidance
- reinforcement learning
- multi agent
- path planning
- control problems
- mobile robot
- dynamic environments
- dynamic programming
- feedback control
- infinite horizon
- function approximation
- path finding
- state space
- optimal control problems
- model free
- markov decision processes
- adaptive control
- control law
- temporal difference
- neural network
- learning algorithm
- fuzzy neural network
- control strategy
- optimal policy
- single agent
- machine learning
- formation control
- real time
- computational intelligence
- search algorithm