IEEE

Model-Free Offline Reinforcement Learning for Linear Quadratic Control

Abstract: This paper investigates the linear quadratic control problem with both process and measurement noise using reinforcement learning. Instead of requiring a system model or real-time controller ...
Quanta Magazine

Using AI, Mathematicians Find Hidden Glitches in Fluid Equations

Nearly 200 years ago, the physicists Claude-Louis Navier and George Gabriel Stokes put the finishing touches on a set of equations that describe how fluids swirl. And for nearly 200 years, the ...
GitHub

Demystifying Reinforcement Learning in Agentic Reasoning

An overview of our research on agentic RL. In this work, we systematically investigate three dimensions of agentic RL: data, algorithms, and reasoning modes. Our findings reveal: Real end-to-end ...
IEEE

Soft Value Iteration for Bellman Equations via Maximum Entropy Reinforcement Learning

Abstract: This work evaluates the effectiveness of entropy-regularized Reinforcement Learning (RL) by contrasting Soft Value Iteration with conventional Bellman-based approaches. Based on the Maximum ...