Regularized Q-learning

Abstract

Q-learning is widely used algorithm in reinforcement learning community. Under the lookup table setting, its convergence is well established. However, its behavior is known to be unstable with the linear function approximation case. This paper develops a new Q-learning algorithm that converges when linear function approximation is used. We prove that simply adding an appropriate regularization term ensures convergence of the algorithm. We prove its stability using a recent analysis tool based on switching system models. Moreover, we experimentally show that it converges in environments where Q-learning with linear function approximation has known to diverge. We also provide an error bound on the solution where the algorithm converges.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylim2022regularized

Related papers

• Stabilizing Q-learning With Linear Architectures For Provably Efficient Learning (2022)0.00
• Q-learning As A Monotone Scheme (2024)0.00
• Q-learning In Regularized Mean-field Games (2020)0.00
• Logistic Q-learning (2020)0.00
• SBEED: Convergent Reinforcement Learning With Nonlinear Function Approximation (2017)0.00
• Target Transfer Q-learning And Its Convergence Analysis (2018)0.00
• Fast Policy Learning For Linear Quadratic Control With Entropy Regularization (2023)0.00
• Finite Horizon Q-learning: Stability, Convergence, Simulations And An Application On Smart Grids (2021)0.00