Author

Jaehwi Lee

h-index 0 View on Semantic Scholar

We have 1 of 1 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Simple Actors and Deep Critics for Scalable Reinforcement Learning

This work revisits where capacity should be invested in an offline actor--critic method and proposes LAC (Light Actor, deep Critic), a lightweight deterministic actor that matches the strongest diffusion- and flow-matching baselines while achieving up to 4x lower inference latency.

Gu-Heon Kang, Jaehwi Lee, Minhae Kwon · 0 citations