Reinforcement Learning

Reinforcement learning (RL) focuses on training agents to make optimal decisions in an environment by learning through trial and error, aiming to maximize cumulative rewards. Current research emphasizes improving RL's efficiency and robustness, particularly in areas like human-in-the-loop training (e.g., using human feedback to refine models), handling uncertainty and sparse rewards, and scaling to complex tasks (e.g., robotics, autonomous driving). Prominent approaches involve various policy gradient methods, Monte Carlo Tree Search, and the integration of large language models for improved decision-making and task decomposition. These advancements are driving progress in diverse fields, including robotics, game playing, and the development of more human-aligned AI systems.

4724papers

Papers - Page 4

March 25, 2025

Optimal Path Planning and Cost Minimization for a Drone Delivery System Via Model Predictive Control
Muhammad Al-Zafar Khan, Jamal Al-Karaki
Zayed University●The Hashemite University
Predictive Control Single Drone Reinforcement Learning Drone Delivery Q$ Learning Optimal Path Planning
Risk-Aware Reinforcement Learning for Autonomous Driving: Improving Safety When Driving through Intersection
Bo Leng, Ran Yu, Wei Han, Lu Xiong, Zhuoren Li, Hailong Huang
Tongji University●the Hong Kong Polytechnic University
Reward Learning Human SAFETY Autonomous Driving Reinforcement Learning Intersection Scenario Risk Aware Reinforcement Learning Risk Awareness
Learning to chain-of-thought with Jensen's evidence lower bound
Yunhao Tang, Sid Wang, Rémi Munos
Meta GenAI●Meta FAIR
Online Reinforcement Learning Reinforcement Learning Policy Gradient Chain of Thought Evidence Piece
Optimizing Language Models for Inference Time Objectives using Reinforcement Learning
Yunhao Tang, Kunhao Zheng, Gabriel Synnaeve, Rémi Munos
Meta GenAI●Meta FAIR
Algorithm Performance Inference Time Language Model Reasoning Datasets Reinforcement Learning
One Framework to Rule Them All: Unifying RL-Based and RL-Free Methods in RLHF
Xin Cai
Independent Researcher
Neural Bandit Proximal Policy Optimization Reinforcement Learning From Human Feedback Reinforcement Learning New Framework Anti Unification
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
Mingyang Chen, Tianpeng Li, Haoze Sun, Yijie Zhou, Chenzheng Zhu, Fan Yang, Zenan Zhou, Weipeng Chen, Haofen Wang, Jeff Z. Pan, Wen Zhang+1
Baichuan Inc.●Tongji University●The University of Edinburgh●Zhejiang University
Positive Reinforcement Reinforcement Learning Reason Giving DH Research Complex Reasoning LeArning Abstract Large Language Model

March 24, 2025

Continual Reinforcement Learning for HVAC Systems Control: Integrating Hypernetworks and Transfer Learning
Gautham Udayakumar Bekal, Ahmed Ghareeb, Ashish Pujari
Enlyte●University of Kirkuk●University of North Carolina at Charlotte
Transfer Learning First Integral Deep Reinforcement Learning Reinforcement Learning Continual Reinforcement Learning Attention Hypernetworks Heating, Ventilation, and Air Conditioning Continual LEArning
A Shared Low-Rank Adaptation Approach to Personalized RLHF
Renpu Liu, Peng Wang, Donghao Li, Cong Shen, Jing Yang
University of Virginia
Reinforcement Learning From Human Feedback Reinforcement Learning Reward Function
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
Brian R. Bartoldson, Siddarth Venkatraman, James Diffenderfer, Moksh Jain, Tal Ben-Nun, Seanie Lee, Minsu Kim, Johan Obando-Ceron+2
Lawrence Livermore National Laboratory●Mila – Quebec AI Institute●Universit´e de Montr´eal●KAIST●CIFAR Fellow
Policy Sampling Diversity Reinforcement Learning Environment Exploration Asynchronous Architecture Reinforcement Learning LeArning Abstract Sparse Reward
Option Discovery Using LLM-guided Semantic Hierarchical Reinforcement Learning
Chak Lam Shek, Pratap Tokekar
University of Maryland
Hierarchical Reinforcement Learning Option Discovery Reinforcement Learning Option Learning LeArning Abstract
Sample-Efficient Reinforcement Learning of Koopman eNMPC
Daniel Mayfrank, Mehmet Velioglu, Alexander Mitsos, Manuel Dahmen
Forschungszentrum Jülich GmbH●RWTH Aachen University●JARA-ENERGY
Sample Efficient Reinforcement Learning Policy Optimization Model Predictive Control Reinforcement Learning Koopman Operator Nonlinear Model Predictive Control
AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models
Le Qiu, Zelai Xu, Qixin Tan, Wenhao Tang, Chao Yu, Yu Wang
Tsinghua University●Beijing Zhongguancun Academy
Autonomous Driving Policy Security Vulnerability Reinforcement Learning Automatic Discovery Autonomous Vehicle Adversarial Policy
Simulation-Driven Balancing of Competitive Game Levels with Reinforcement Learning
Florian Rupp, Manuel Eberhardinger, Kai Eckert
Balancing Strategy Procedural Content Generation Neural MMO Two Player Reinforcement Learning Dynamic Balance Tile Based
FF-SRL: High Performance GPU-Based Surgical Simulation For Robot Learning
Diego Dall'Alba, Michał Nasket, Sabina Kaminska, Przemysław Korzeniowski
Sano Centre for Computational Medicine●University of Verona
Surgical Simulator High Performance Robotic Surgery Reinforcement Learning LeArning Abstract Robot Person
Reinforcement Learning in Switching Non-Stationary Markov Decision Processes: Algorithms and Convergence Analysis
Mohsen Amiri, Sindri Magnússon
Stockholm University
Policy Iteration Markov Chain Practical Algorithm Markov Decision Process Complex Process Convergence Analysis Non Stationary Environment Reinforcement Learning
Teaching LLMs for Step-Level Automatic Math Correction via Reinforcement Learning
Junsong Li, Jie Zhou, Yutao Yang, Bihao Zhan, Qianjun Pan, Yuyang Ding, Qin Chen, Jiang Bo, Xin Lin, Liang He
East China Normal University
Reinforcement Learning Fine Grained Positive Reinforcement Medical LLM RL Method LeArning Abstract
Finite-Time Bounds for Two-Time-Scale Stochastic Approximation with Arbitrary Norm Contractions and Markovian Noise
Siddharth Chandak, Shaan Ul Haque, Nicholas Bambos
Stanford University●Georgia Institute of Technology
Reinforcement Learning Stochastic Approximation Q Learning Finite Time Temporal Prior
Agent-based Modeling meets the Capability Approach for Human Development: Simulating Homelessness Policy-making
Alba Aguilera, Nardine Osman, Georgina Curto
IIIA-CSIC●United Nations University Institute in Macau
Reinforcement Learning Agent Based Agent Based Simulation Development Activity Policy Reproducibility Capability Based Human Generated
Reinforcement Learning for Adaptive Planner Parameter Tuning: A Perspective on Hierarchical Architecture
Lu Wangtao, Wei Yufei, Xu Jiadong, Jia Wenhao, Li Liang, Xiong Rong, Wang Yue
Zhejiang University●Zhejiang University of Technology
Autonomous Robot Navigation Layer Selection Visual Perspective Parameter Tuning Reinforcement Learning Planning Algorithm
Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners
Wen Zheng Terence Ng, Jianda Chen, Yuan Xu, Tianwei Zhang
Nanyang Technological University●Continental Automotive Singapore
Trajectory Wise Reward Preference Inference Intermediate Latent Diffusion Explainer Latent Preference Visual Planner Adaptation Concern Reinforcement Learning Conditional Diffusion Model

Reinforcement Learning

Papers - Page 4

Optimal Path Planning and Cost Minimization for a Drone Delivery System Via Model Predictive Control

Risk-Aware Reinforcement Learning for Autonomous Driving: Improving Safety When Driving through Intersection

Learning to chain-of-thought with Jensen's evidence lower bound

Optimizing Language Models for Inference Time Objectives using Reinforcement Learning

One Framework to Rule Them All: Unifying RL-Based and RL-Free Methods in RLHF

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Continual Reinforcement Learning for HVAC Systems Control: Integrating Hypernetworks and Transfer Learning

A Shared Low-Rank Adaptation Approach to Personalized RLHF

Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training

Option Discovery Using LLM-guided Semantic Hierarchical Reinforcement Learning

Sample-Efficient Reinforcement Learning of Koopman eNMPC

AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models

Simulation-Driven Balancing of Competitive Game Levels with Reinforcement Learning

FF-SRL: High Performance GPU-Based Surgical Simulation For Robot Learning

Reinforcement Learning in Switching Non-Stationary Markov Decision Processes: Algorithms and Convergence Analysis

Teaching LLMs for Step-Level Automatic Math Correction via Reinforcement Learning

Finite-Time Bounds for Two-Time-Scale Stochastic Approximation with Arbitrary Norm Contractions and Markovian Noise

Agent-based Modeling meets the Capability Approach for Human Development: Simulating Homelessness Policy-making

Reinforcement Learning for Adaptive Planner Parameter Tuning: A Perspective on Hierarchical Architecture

Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners