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

September 27, 2024

ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning
Jannis Becktepe, Julian Dierkes, Carolin Benjamins, Aditya Mohan, David Salinas, Raghu Rajan, Frank Hutter, Holger Hoos, Marius Lindauer, Theresa Eimer
Reinforcement Learning Hyperparameter Optimization Extension Study Related Hyperparameters Benchmark Design Hyperparameter Landscape
Climate Adaptation with Reinforcement Learning: Experiments with Flooding and Transportation in Copenhagen
Miguel Costa, Morten W. Petersen, Arthur Vandervoort, Martin Drews, Karyn Morrissey, Francisco C. Pereira
Reinforcement Learning Optical Experiment Climate Change Adaptation Extreme Precipitation Urban Flood Adaptation Strategy
Cost-Aware Dynamic Cloud Workflow Scheduling using Self-Attention and Evolutionary Reinforcement Learning
Ya Shen, Gang Chen, Hui Ma, Mengjie Zhang
Reinforcement Learning Self Attention Scheduling Policy Cost Aware
VickreyFeedback: Cost-efficient Data Construction for Reinforcement Learning from Human Feedback
Guoxi Zhang, Jiuding Duan
Reinforcement Learning Human Feedback Fine Tuned LLM Preference Datasets Dataset Creation Expert Feedback Preference Dataset
CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Models
Kanghyun Ryu, Qiayuan Liao, Zhongyu Li, Koushil Sreenath, Negar Mehr
Reinforcement Learning Skill Learning Humanoid Locomotion Complex Robotic Task Aware Curriculum Learning Curriculum
iWalker: Imperative Visual Planning for Walking Humanoid Robot
Xiao Lin, Yuhao Huang, Taimeng Fu, Xiaobin Xiong, Chen Wang
Reinforcement Learning Humanoid Robot Visual Planning Imperative Learning Rollator Walker

September 26, 2024

Improving Agent Behaviors with RL Fine-tuning for Autonomous Driving
Zhenghao Peng, Wenjie Luo, Yiren Lu, Tianyi Shen, Cole Gulino, Ari Seff, Justin Fu
Reinforcement Learning Autonomous Driving Fine Tuning Motion Forecasting Agent Behavior Autonomous Driving Research Driving Planning
Criticality and Safety Margins for Reinforcement Learning
Alexander Grushin, Walt Woods, Alvaro Velasquez, Simon Khan
Reinforcement Learning Autonomous Agent Criticality Ordered Spin Sequence Criticality Analysis Safety Margin
Autonomous Network Defence using Reinforcement Learning
Myles Foley, Chris Hicks, Kate Highnam, Vasilios Mavroudis
Reinforcement Learning Autonomous Agent Cyber Attack Novel Reinforcement Learning Autonomous Network
A Survey on Neural Architecture Search Based on Reinforcement Learning
Wenzhu Shao
Reinforcement Learning Deep Learning Timely Survey Neural Architecture Search Hyperparameter Optimization Deep Learning Architecture Optimal Hyperparameters
LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots
Peilin Wu, Weiji Xie, Jiahang Cao, Hang Lai, Weinan Zhang
Reinforcement Learning Real World Legged Robot Legged Locomotion Policy Adaptation Continual Training Policy Generation
FactorSim: Generative Simulation via Factorized Representation
Fan-Yun Sun, S. I. Harini, Angela Yi, Yihan Zhou, Alex Zook, Jonathan Tremblay, Logan Cross, Jiajun Wu, Nick Haber
Reinforcement Learning Markov Decision Process Simulation Study Structured Representation Stochastic Simulation Complex Generative Benchmarking Generative
Learning Occlusion-aware Decision-making from Agent Interaction via Active Perception
Jie Jia, Yiming Shu, Zhongxue Gan, Wenchao Ding
Reinforcement Learning LeArning Abstract Visual Reinforcement Learning Active Perception Occlusion Sensitivity Analysis Agent Interaction
Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards
Heejin Do, Sangwon Ryu, Gary Geunbae Lee
Reinforcement Learning Reward Model Essay Scoring Autoregressive Generation Trait Estimation
Verti-Selector: Automatic Curriculum Learning for Wheeled Mobility on Vertically Challenging Terrain
Tong Xu, Chenhui Pan, Xuesu Xiao
Reinforcement Learning Curriculum Learning Road Environment Complex Terrain Network Selection Training Environment Kinodynamic Model Wheeled Mobility

September 25, 2024

Post-hoc Reward Calibration: A Case Study on Length Bias
Zeyu Huang, Zihan Qiu, Zili Wang, Edoardo M. Ponti, Ivan Titov
Reinforcement Learning Case Study Reward Model Length Bias
Spiders Based on Anxiety: How Reinforcement Learning Can Deliver Desired User Experience in Virtual Reality Personalized Arachnophobia Treatment
Athar Mahmoudi-Nejad, Matthew Guzdial, Pierre Boulanger
Reinforcement Learning User Experience Human Reaction FEAR Speech Anxiety Detection Anxiety Disorder SPIDER Max
Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference
Qining Zhang, Lei Ying
Reinforcement Learning Human Feedback Policy Gradient Direct Preference Optimization Reward Value Reward Inference
Topological Foundations of Reinforcement Learning
David Krame Kadurha
Reinforcement Learning Markov Decision Process Reinforcement Learning Problem Compression Operator
Learning with Dynamics: Autonomous Regulation of UAV Based Communication Networks with Dynamic UAV Crew
Ran Zhang, Bowei Li, Liyuan Zhang, Jiang (Linda)Xie, Miao Wang
Reinforcement Learning LeArning Abstract Unmanned Aerial Vehicle

Reinforcement Learning

Papers

ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning

Climate Adaptation with Reinforcement Learning: Experiments with Flooding and Transportation in Copenhagen

Cost-Aware Dynamic Cloud Workflow Scheduling using Self-Attention and Evolutionary Reinforcement Learning

VickreyFeedback: Cost-efficient Data Construction for Reinforcement Learning from Human Feedback

CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Models

iWalker: Imperative Visual Planning for Walking Humanoid Robot

Improving Agent Behaviors with RL Fine-tuning for Autonomous Driving

Criticality and Safety Margins for Reinforcement Learning

Autonomous Network Defence using Reinforcement Learning

A Survey on Neural Architecture Search Based on Reinforcement Learning

LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots

FactorSim: Generative Simulation via Factorized Representation

Learning Occlusion-aware Decision-making from Agent Interaction via Active Perception

Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards

Verti-Selector: Automatic Curriculum Learning for Wheeled Mobility on Vertically Challenging Terrain

Post-hoc Reward Calibration: A Case Study on Length Bias

Spiders Based on Anxiety: How Reinforcement Learning Can Deliver Desired User Experience in Virtual Reality Personalized Arachnophobia Treatment

Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference

Topological Foundations of Reinforcement Learning

Learning with Dynamics: Autonomous Regulation of UAV Based Communication Networks with Dynamic UAV Crew