Author name: Donghwan Lee

Beyond the Bellman Fixed Point: Geometry and Fast Policy Identification in Value Iteration

Donghwan Lee / April 22, 2026

arXiv:2604.17457v2 Announce Type: replace-cross
Abstract: Dynamic programming is one of the most fundamental methodologies for solving Markov decision problems. Among its many variants, Q-value iteration (Q-VI) is particularly important due to its con…

cs.AI, cs.LG, cs.SY, eess.SY

Lyapunov-Certified Direct Switching Theory for Q-Learning

Donghwan Lee / April 22, 2026

arXiv:2604.19569v1 Announce Type: new
Abstract: Q-learning is one of the most fundamental algorithms in reinforcement learning. We analyze constant-stepsize Q-learning through a direct stochastic switching system representation. The key observation is…