← authors · overview

• IRLAS: Inverse Reinforcement Learning for Architecture Search
  2018 · 8 citations
• Policy Continuation with Hindsight Inverse Dynamics
  2019 · 7 citations
• Novel Policy Seeking with Constrained Optimization
  2020 · 3 citations
• Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning
  2025
• Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving
  2025
• OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification
  2025
• Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning
  2025
• Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning
  2025
• Visual Agentic Reinforcement Fine-Tuning
  2025
• Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
  2025
• Improving On-policy Learning with Statistical Reward Accumulation
  2018
• Biased Estimates of Advantages over Path Ensembles
  2019
• Evolutionary Stochastic Policy Distillation
  2020