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.

Papers

October 31, 2024

Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI
Hadassah Harland, Richard Dazeley, Peter Vamplew, Hashini Senaratne, Bahareh Nakisa, Francisco Cruz
Reinforcement Learning Artificial Intelligence Multi Objective Reinforcement Learning Socio Technical System Alignment Tuning
RA-RLHF: Provably Efficient Risk-Aware Reinforcement Learning Human Feedback
Yujie Zhao, Jose Efraim Aguilar Escamill, Weyl Lu, Huazheng Wang
Reinforcement Learning LeArning Abstract Risk Sensitive Positive Reinforcement Preference Based Reinforcement Learning Quantile Temporal Difference Risk Sensitive Algorithm
Simulating User Agents for Embodied Conversational-AI
Daniel Philipov, Vardhan Dongre, Gokhan Tur, Dilek Hakkani-Tür
Reinforcement Learning Human Robot Embodied Agent Natural Language Communication Embodied Conversational Agent User Behavior Simulation

October 30, 2024

Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm
Sattar Vakili, Julia Olkhovskaya
Reinforcement Learning LeArning Abstract Kernel Ridge Regression Regret Guarantee Kernel Approximation Average Reward Reinforcement Learning
Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation
Stefan Stojanovic, Yassir Jedra, Alexandre Proutiere
Reinforcement Learning Optimal Policy Model Free Policy Iteration Low Rank Matrix Free Learning Matrix Estimation
Stepping Out of the Shadows: Reinforcement Learning in Shadow Mode
Philipp Gassert, Matthias Althoff
Reinforcement Learning Robotics Domain Reinforcement Learning Agent Model Based Cross Over Step Quantum Shadow
Resource Governance in Networked Systems via Integrated Variational Autoencoders and Reinforcement Learning
Qiliang Chen, Babak Heydari
Reinforcement Learning Deep Reinforcement Learning Supervised Autoencoder Multi Agent System Variational Autoencoders Variational Method Resource Management Networked System
COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences
Yixin Liu, Argyris Oikonomou, Weiqiang Zheng, Yang Cai, Arman Cohan
Reinforcement Learning Medical LLM Preference Feedback Policy Optimization General Text Two Player Zero Sum Automatic Alignment Nash Equilibrium Policy Meta Algorithm
Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks
Michael Matthews, Michael Beukman, Chris Lu, Jakob Foerster
Reinforcement Learning Training Data Physic Based Physical Reasoning Generalist Agent Reinforcement Learning Environment
Offline Reinforcement Learning and Sequence Modeling for Downlink Link Adaptation
Samuele Peri, Alessio Russo, Gabor Fodor, Pablo Soldati
Reinforcement Learning Offline Reinforcement Learning Adaptation Concern Sequence Modeling Radio Access Network Conservative Q Learning Downlink Communication
Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback
Qinqing Zheng, Mikael Henaff, Amy Zhang, Aditya Grover, Brandon Amos
Reinforcement Learning Agent Smith Sparse Reward Large Language Online Service Intrinsic Reward Model Improvement
DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data
Hanyang Chen, Yang Jiang, Shengnan Guo, Xiaowei Mao, Youfang Lin, Huaiyu Wan
Reinforcement Learning Diffusion Model Traffic Data Traffic Signal Control Missing Data Traffic Efficiency Signal Control
Permutation Invariant Learning with High-Dimensional Particle Filters
Akhilan Boopathy, Aneesh Muppidi, Peggy Yang, Abhiram Iyer, William Yue, Ila Fiete
Reinforcement Learning Particle Filter Sequential Learning Permutation Invariant

October 29, 2024

Solving Minimum-Cost Reach Avoid using Reinforcement Learning
Oswin So, Cheng Ge, Chuchu Fan
Reinforcement Learning Reach Avoid Sub Optimal Policy
Environment as Policy: Learning to Race in Unseen Tracks
Hongze Wang, Jiaxu Xing, Nico Messikommer, Davide Scaramuzza
Reinforcement Learning Optimal Policy Environment Feature Health Policy Recommendation Complex Robotic System Drone Racing Unseen Viewpoint
Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning
Jianlan Luo, Charles Xu, Jeffrey Wu, Sergey Levine
Reinforcement Learning Human in the Loop Robot Skill Manipulation Policy Dexterous Robotic Manipulation Vision Based Reinforcement Learning

October 28, 2024

Identifying Selections for Unsupervised Subtask Discovery
Yiwen Qiu, Yujia Zheng, Kun Zhang
Reinforcement Learning View Selection Long Horizon Task Policy Generalization Subtask Assignment
The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure
Tyler Sam, Yudong Chen, Christina Lee Yu
Reinforcement Learning Continuum Limit Inner Structure Transferable Representation Intermediate Latent LOw Rank Transfer Reinforcement Learning
A Multi-Agent Reinforcement Learning Testbed for Cognitive Radio Applications
Sriniketh Vangaru, Daniel Rosen, Dylan Green, Raphael Rodriguez, Maxwell Wiecek, Amos Johnson, Alyse M. Jones, William C. Headley
Reinforcement Learning Financial Application Multi Agent Reinforcement Learning Reinforcement Learning Agent Cognitive Radio
Exploring reinforcement learning for incident response in autonomous military vehicles
Henrik Madsen, Gudmund Grov, Federico Mancini, Magnus Baksaas, Åvald Åslaugson Sommervoll
Reinforcement Learning Unmanned Ground Vehicle Military Application Cyber Defense Unmanned Vehicle Autonomous Cyber Incident Management

Reinforcement Learning

Papers

Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI

RA-RLHF: Provably Efficient Risk-Aware Reinforcement Learning Human Feedback

Simulating User Agents for Embodied Conversational-AI

Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm

Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation

Stepping Out of the Shadows: Reinforcement Learning in Shadow Mode

Resource Governance in Networked Systems via Integrated Variational Autoencoders and Reinforcement Learning

COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences

Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks

Offline Reinforcement Learning and Sequence Modeling for Downlink Link Adaptation

Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback

DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data

Permutation Invariant Learning with High-Dimensional Particle Filters

Solving Minimum-Cost Reach Avoid using Reinforcement Learning

Environment as Policy: Learning to Race in Unseen Tracks

Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning

Identifying Selections for Unsupervised Subtask Discovery

The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure

A Multi-Agent Reinforcement Learning Testbed for Cognitive Radio Applications

Exploring reinforcement learning for incident response in autonomous military vehicles