← Search

Letian Tao

2 accepted papers

2026

Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation

ICLR 2026oral

Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling process, they still face a trade-off between expressiveness…

Cited by 0SourceScholar
2026

Taming the Aleatoric Impulse in Off-Policy Reinforcement Learning

ICML 2026poster

Off-policy reinforcement learning is vulnerable to overestimation bias, which is rooted in the total value uncertainty. However, existing methods typically misaddress this by targeting the epistemic component, neglecting the aleatoric component. We identify for the first time that this oversight fai…

Cited by 0SourceScholar