Reinforcement Learning
EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine Jiayi Weng Min Lin
Deep Reinforcement Learning (RL) has made remarkable progress in the past years.
Efficient Planning in Large MDPs with Weak Linear Function Approximation
Roshan Shariff & Csaba Szepesvรกri
In this paper we consider the intersection of these two problem formulations.
Accelerating Quadratic Optimization with Reinforcement Learning
Solving quadratic programs (QPs) efficiently is critical to applications in finance, robotic control and operations research.
policy improvement $
Setting up a well-designed reward function has been challenging for many reinforcement learning applications.
Avoiding Side Effects By Considering Future Tasks Victoria Krakovna
Designing reward functions for a reinforcement learning agent is often a difficult task.
Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation
With increasing success in reinforcement learning (RL), there is broad interest in applying these methods to real-world settings. This has brought exciting progress in offline RL and off-policy policy evaluation (OPPE).
Safe Policy Optimization with Local Generalized Linear Function Approximations
We propose a novel algorithm, SPO-LF, that optimizes an agent's policy while
R-learning in actor-critic model offers a biologically relevant mechanism for sequential decision-making
In everyday life we repeatedly face sequential stay-or-leave decisions.