← authors · overview

• Suphx: Mastering Mahjong with Deep Reinforcement Learning
  2020 · 85 citations
• Return-Based Contrastive Representation Learning for Reinforcement Learning
  2021 · 18 citations
• You May Not Need Ratio Clipping in PPO
  2022 · 7 citations
• De novo Drug Design using Reinforcement Learning with Multiple GPT Agents
  2024 · 6 citations
• UniGenX: a unified generative foundation model that couples sequence, structure and function to accelerate scientific design across proteins, molecules and materials
  2025 · 5 citations
• Proactive Constrained Policy Optimization with Preemptive Penalty
  2025 · 2 citations
• ABot-Claw: A Foundation for Persistent, Cooperative, and Self-Evolving Robotic Agents
  2026
• ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation
  2026
• Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning
  2025
• A Region of Interest Focused Triple UNet Architecture for Skin Lesion Segmentation
  2023
• Reinforcement Learning from Bagged Reward
  2024
• Learning-based Traversability Costmap for Autonomous Off-road Navigation
  2024
• Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
  2023