pith. sign in

Donghwan Lee

Identifiers

  • name variant Donghwan Lee 0.60 · backfill

Papers (17)

  1. Sign-Separated Finite-Time Error Analysis of Q-Learning cs.AI · 2026 · author #1
  2. Switching-Geometry Analysis of Deflated Q-Value Iteration math.OC · 2026 · author #1
  3. A Switching System Theory of Q-Learning with Linear Function Approximation cs.LG · 2026 · author #1
  4. Soft Deterministic Policy Gradient with Gaussian Smoothing cs.LG · 2026 · author #2
  5. Safe-Support Q-Learning: Learning without Unsafe Exploration cs.LG · 2026 · author #3
  6. Lyapunov-Certified Direct Switching Theory for Q-Learning cs.LG · 2026 · author #1
  7. Beyond the Bellman Fixed Point: Geometry and Fast Policy Identification in Value Iteration math.OC · 2026 · author #1
  8. Contraction-Aligned Analysis of Soft Bellman Residual Minimization with Weighted Lp-Norm for Markov Decision Problem cs.LG · 2026 · author #3
  9. Finite-Time Analysis of Q-Value Iteration for General-Sum Stackelberg Games cs.LG · 2026 · author #2
  10. R-GTD: A Geometric Analysis of Gradient Temporal-Difference Learning in Singular Regimes cs.LG · 2026 · author #2
  11. Bellman Residual Minimization for Control: Geometry, Stationarity, and Convergence cs.LG · 2026 · author #1
  12. Toward a Unified Lyapunov-Certified ODE Convergence Analysis of Smooth Q-Learning with p-Norms cs.LG · 2024 · author #1
  13. Learning to Communicate: A Machine Learning Framework for Heterogeneous Multi-Agent Robotic Systems cs.RO · 2018 · author #6
  14. Supplemental Material For "Primal-Dual Q-Learning Framework for LQR Design" math.OC · 2018 · author #1
  15. Hidden Markov Model Estimation-Based Q-learning for Partially Observable Markov Decision Process cs.LG · 2018 · author #2
  16. Dynamic Programming for POMDP with Jointly Discrete and Continuous State-Spaces math.OC · 2018 · author #1
  17. Primal-Dual Algorithm for Distributed Reinforcement Learning: Distributed GTD math.OC · 2018 · author #1

Mentions

  • 2605.11021 #1 · arxiv_oai · confidence 0.70 Donghwan Lee
  • 2605.10811 #1 · arxiv_oai · confidence 0.70 Donghwan Lee
  • 2605.16103 #1 · arxiv_oai · confidence 0.70 Donghwan Lee

Frequent Coauthors