Robust Reinforcement Learning using Offline Data
This work addresses robust policy learning for real-world RL applications with offline data, offering a systematic solution to challenges like data collection and optimization, though it appears incremental as it builds on existing robust RL frameworks.
The authors tackled robust reinforcement learning using only offline data, proposing Robust Fitted Q-Iteration (RFQI) to learn policies robust against model parameter uncertainty, and demonstrated superior performance on standard benchmarks with theoretical guarantees.
The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the uncertainty in model parameters. Parameter uncertainty commonly occurs in many real-world RL applications due to simulator modeling errors, changes in the real-world system dynamics over time, and adversarial disturbances. Robust RL is typically formulated as a max-min problem, where the objective is to learn the policy that maximizes the value against the worst possible models that lie in an uncertainty set. In this work, we propose a robust RL algorithm called Robust Fitted Q-Iteration (RFQI), which uses only an offline dataset to learn the optimal robust policy. Robust RL with offline data is significantly more challenging than its non-robust counterpart because of the minimization over all models present in the robust Bellman operator. This poses challenges in offline data collection, optimization over the models, and unbiased estimation. In this work, we propose a systematic approach to overcome these challenges, resulting in our RFQI algorithm. We prove that RFQI learns a near-optimal robust policy under standard assumptions and demonstrate its superior performance on standard benchmark problems.