<ul><li>Researchers propose a class of instrument variable-based reinforcement learning (IV-RL) algorithms to address reinforcement bias in data analysis.</li><li>The interaction between data generation and data analysis leads to reinforcement bias, exacerbating the endogeneity problem.</li><li>The proposed IV-RL algorithms are incorporated into a stochastic approximation framework and have theoretical properties.</li><li>The analysis also includes formulas for inference on optimal policies and highlights how intertemporal dependencies affect inference.</li></ul>

Asymptotic Theory for IV-Based Reinforcement Learning with Potential Endogeneity

Discover more