Donghwan Lee
PulseAugur coverage of Donghwan Lee — every cluster mentioning Donghwan Lee across labs, papers, and developer communities, ranked by signal.
-
Q-learning theory advanced with new error analysis and switching system framework · 2 sources tracked
Two new research papers analyze Q-learning, a fundamental reinforcement learning algorithm, from different theoretical perspectives. The first paper focuses on the overestimation bias inherent in Q-learning, decomposing…
-
MATANet advances marine species recognition with context and hierarchy awareness
Researchers have developed MATANet, a novel framework designed for the fine-grained recognition of marine species, particularly in challenging underwater environments. This network incorporates a Multi-Context Environme…
-
New diffusion model framework enhances pose-guided person image synthesis
Researchers have developed a new framework called Fusion Embedding for PGPIS using a Diffusion Model (FPDM) to improve the synthesis of person images based on specified poses. This method explicitly aligns fused source-…
-
New Q-learning theory offers tighter convergence rate analysis
Researchers have developed a novel theoretical framework for analyzing Q-learning, a fundamental algorithm in reinforcement learning. This new approach views Q-learning through the lens of switching systems, deriving a …
-
New research explores Bellman residual minimization for control tasks in reinforcement learning
This paper introduces foundational results for Bellman residual minimization applied to policy optimization in Markov decision problems. While dynamic programming is more common, Bellman residual minimization offers adv…