Twice Regularized Mdps And The Equivalence Between Robustness And Regularization

Abstract

Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and limits scalability in both learning and planning. On the other hand, regularized MDPs show more stability in policy learning without impairing time complexity. Yet, they generally do not encompass uncertainty in the model dynamics. In this work, we aim to learn robust MDPs using regularization. We first show that regularized MDPs are a particular instance of robust MDPs with uncertain reward. We thus establish that policy iteration on reward-robust MDPs can have the same time complexity as on regularized MDPs. We further extend this relationship to MDPs with uncertain transitions: this leads to a regularization term with an additional dependence on the value function. We finally generalize regularized MDPs to twice regularized MDPs (R\(\{\}^2\) MDPs), i.e

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyderman2021twice

Related papers

• Twice Regularized Markov Decision Processes: The Equivalence Between Robustness And Regularization (2023)0.00
• Solving Non-rectangular Reward-robust Mdps Via Frequency Regularization (2023)0.00
• Robust Anytime Learning Of Markov Decision Processes (2022)0.00
• Efficient Policy Optimization In Robust Constrained Mdps With Iteration Complexity Guarantees (2025)0.00
• Solving Robust Mdps Through No-regret Dynamics (2023)0.00
• Lyapunov Robust Constrained-mdps: Soft-constrained Robustly Stable Policy Optimization Under Model Uncertainty (2021)0.00
• Distributional Robustness And Regularization In Reinforcement Learning (2020)0.00
• A Regularized Approach To Sparse Optimal Policy In Reinforcement Learning (2019)0.00