Skip to content

Author

Honghao Wei

We have 4 of 24 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 Oct 2026

Rate-Optimal Algorithm for Adversarial Linear CMDPs

We study episodic adversarial linear constrained Markov decision processes (CMDPs) with unknown transitions, where both the loss and constraint functions may vary adversarially across episodes. The best previous algorithm achieves $\widetilde{\mathcal{O}}(K^{3/4})$ regret and cumulative constraint violation, leaving a...

Kihyun Yu, Hong-Hao Wei, Dabeen Lee · 0 citations
#artificial intelligence Preprint Oct 2026

Reinforcement Learning with Conformal Action Sets: An Application to Sequential Recommendation

Sequential recommenders typically use a fixed slate size even though the number of useful alternatives changes within a session. We propose Reinforcement Learning with Calibrated Pruning (RLCP), which adapts the retained action set using critic scores and an online threshold. The threshold is updated from binary feedba...

Wen-Wen Si, Hong-Hao Wei · 0 citations
#machine learning Preprint Oct 2026

Rate-Optimal Algorithm for Adversarial Linear CMDPs

We study episodic adversarial linear constrained Markov decision processes (CMDPs) with unknown transitions, where both the loss and constraint functions may vary adversarially across episodes. The best previous algorithm achieves $\widetilde{\mathcal{O}}(K^{3/4})$ regret and cumulative constraint violation, leaving a...

Kihyun Yu, Hong-Hao Wei, Dabeen Lee · 0 citations
Preprint Aug 2026

Boundary-Seeking Policy Gradient for Safe Reinforcement Learning

This work introduces Boundary-Seeking Policy Gradient (BSPG), a first-order method whose update combines a tangential component that improves reward while preserving cost to first order with a signed, residual-driven normal component that regulates the policy toward the active boundary from either side.

Chenhua Fan, Jiahui Zhu, Yuhang Zhang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.