Reinforcement Learning with Continuous Actions Under Unmeasured Confounding
By: Yuhan Li , Eugene Han , Yifan Hu and more
Potential Business Impact:
Teaches computers to make the best choices.
This paper addresses the challenge of offline policy learning in reinforcement learning with continuous action spaces when unmeasured confounders are present. While most existing research focuses on policy evaluation within partially observable Markov decision processes (POMDPs) and assumes discrete action spaces, we advance this field by establishing a novel identification result to enable the nonparametric estimation of policy value for a given target policy under an infinite-horizon framework. Leveraging this identification, we develop a minimax estimator and introduce a policy-gradient-based algorithm to identify the in-class optimal policy that maximizes the estimated policy value. Furthermore, we provide theoretical results regarding the consistency, finite-sample error bound, and regret bound of the resulting optimal policy. Extensive simulations and a real-world application using the German Family Panel data demonstrate the effectiveness of our proposed methodology.
Similar Papers
Quantile-Optimal Policy Learning under Unmeasured Confounding
Machine Learning (Stat)
Finds best decisions even with missing info.
Automatic Reward Shaping from Confounded Offline Data
Artificial Intelligence
Makes AI learn safely from bad past game experiences.
Model-Based Reinforcement Learning Under Confounding
Machine Learning (CS)
Lets computers learn from past mistakes without seeing everything.