Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets.
Yifei MinTianhao WangRuitu XuZhaoran WangMichael I. JordanZhuoran YangPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- function approximators
- matching algorithm
- online learning
- markov chain
- state space
- image matching
- candidate matches
- learning agent
- complex domains
- lower bound
- electronic commerce
- upper bound
- dynamic programming
- pattern matching
- learning algorithm
- matching process
- partial matching
- confidence bounds
- loss function
- reinforcement learning agents
- false matches
- markov model
- shape matching
- learning problems
- markov decision processes
- optimal policy