Shengbo Eben Li

Latest

• Model-Free Safe Reinforcement Learning through Neural Barrier Certificate
• Policy-Iteration-Based Finite-Horizon Approximate Dynamic Programming for Continuous-Time Nonlinear Optimal Control
• Flow-based Recurrent Belief State Learning for POMDPs
• Reachability Constrained Reinforcement Learning
• Performance-Driven Controller Tuning via Derivative-Free Reinforcement Learning
• Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning
• Model-Based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian
• Model-based Actor-Critic with Chance Constraint for Stochastic System
• Belief State Separated Reinforcement Learning for Autonomous Vehicle Decision Making under Uncertainty
• Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning
• Enable Faster and Smoother Spatio-Temporal Trajectory Planning for Autonomous Vehicles in Constrained Dynamic Environment
• Interpretable End-to-End Urban Autonomous Driving with Latent Deep Reinforcement Learning
• Reinforced Optimal Estimator
• Intention-aware Long Horizon Trajectory Prediction of Surrounding Vehicles using Dual LSTM Networks
• Continuous Decision Making for On-Road Autonomous Driving under Uncertain and Interactive Environments