Least-Restrictive Multi-Agent Collision Avoidance via Deep Meta Reinforcement Learning and Optimal Control.
Salar AsayeshMo ChenMehran MehrandezhKamal GuptaPublished in: CoRR (2021)
Keyphrases
- optimal control
- collision avoidance
- reinforcement learning
- multi agent
- path planning
- control problems
- mobile robot
- dynamic programming
- dynamic environments
- infinite horizon
- feedback control
- function approximation
- state space
- learning algorithm
- reinforcement learning algorithms
- path finding
- optimal policy
- model free
- fuzzy neural network
- single agent
- machine learning
- optimal control problems
- control law
- markov decision processes
- temporal difference
- actor critic
- formation control
- linear quadratic
- policy gradient
- real time