Interaction-Grounded Learning for Contextual Markov Decision Processes with Personalized Feedback
This work addresses a bottleneck in applying interaction-grounded learning to modern sequential tasks, offering a solution for personalized feedback in multi-turn interactions, though it is incremental as it extends prior single-step methods to the multi-step setting.
The paper tackles the problem of learning from indirect feedback in sequential decision-making systems, such as multi-turn LLM deployments, by proposing a computationally efficient algorithm for contextual episodic MDPs with personalized feedback, achieving sublinear regret guarantees and demonstrating effectiveness on synthetic and real-world datasets.
In this paper, we study Interaction-Grounded Learning (IGL) [Xie et al., 2021], a paradigm designed for realistic scenarios where the learner receives indirect feedback generated by an unknown mechanism, rather than explicit numerical rewards. While prior work on IGL provides efficient algorithms with provable guarantees, those results are confined to single-step settings, restricting their applicability to modern sequential decision-making systems such as multi-turn Large Language Model (LLM) deployments. To bridge this gap, we propose a computationally efficient algorithm that achieves a sublinear regret guarantee for contextual episodic Markov Decision Processes (MDPs) with personalized feedback. Technically, we extend the reward-estimator construction of Zhang et al. [2024a] from the single-step to the multi-step setting, addressing the unique challenges of decoding latent rewards under MDPs. Building on this estimator, we design an Inverse-Gap-Weighting (IGW) algorithm for policy optimization. Finally, we demonstrate the effectiveness of our method in learning personalized objectives from multi-turn interactions through experiments on both a synthetic episodic MDP and a real-world user booking dataset.