← authors · overview

• Qualitative Measurements of Policy Discrepancy for Return-Based Deep Q-Network
  2018 · 22 citations
• A Unified Approach for Multi-step Temporal-Difference Learning with Eligibility Traces in Reinforcement Learning
  2018 · 16 citations
• Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization
  2025 · 10 citations
• Policy Optimization with Stochastic Mirror Descent
  2019 · 2 citations
• FedAFD: Multimodal Federated Learning via Adversarial Fusion and Distillation
  2026
• Neural-Driven Image Editing
  2025
• Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization
  2025
• Expected Sarsa($λ$) with Control Variate for Variance Reduction
  2019
• Gradient Q$(σ, λ)$: A Unified Algorithm with Function Approximation for Reinforcement Learning
  2019
• On Convergence of Gradient Expected Sarsa($λ$)
  2020
• TinyLight: Adaptive Traffic Signal Control on Devices with Extremely Limited Resources
  2022