Zhenghai Xue

7 papers · 2021–2025 · 3 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (3) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (14)

Conferences

ICLR (4) NIPS (2) ICML (1)

Top co-authors

Bo An (5) Shuicheng Yan (3) Quanyi Li (1) Billel Mokeddem (1) Safa Messaoud (1) Dong Zheng (1) Xinrun Wang (1) Zhihan Liu (1) Feng Xu (1) Sanjay Chawla (1)

Keywords

reinforcement learning (1) policy optimization (1) domain adaptation (1) regret minimization (1) off-policy reinforcement learning (1) data efficiency (1) experience replay (1) temporal difference error (1) dynamics shift (1) prioritized sampling (1) stationary state distribution (1) homomorphous mdp (1)

Papers

AgentStudio: A Toolkit for Building General Virtual Agents ICLR 2025

Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning ICML 2025

Policy Optimization under Imperfect Human Interactions with Agent-Gated Shared Autonomy ICLR 2025

S$2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic ICLR 2024

Guarded Policy Optimization with Imperfect Online Demonstrations ICLR 2023

State Regularized Policy Optimization on Data with Dynamics Shift NIPS 2023

Regret Minimization Experience Replay in Off-Policy Reinforcement Learning NIPS 2021