Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets.
Yifei MinTianhao WangRuitu XuZhaoran WangMichael I. JordanZhuoran YangPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- matching algorithm
- partial matching
- state space
- markov chain
- markov decision processes
- candidate matches
- false matches
- markov model
- function approximation
- multi agent
- lower bound
- keypoints
- online learning
- shape matching
- reward function
- electronic commerce
- learning algorithm
- function approximators
- matching process
- image matching
- temporal difference
- model free
- reinforcement learning algorithms
- learning agent
- dynamic programming
- previously learned
- feature points