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

July 24, 2024

SoNIC: Safe Social Navigation with Adaptive Conformal Inference and Constrained Reinforcement Learning
Jianpeng Yao, Xiaopan Zhang, Yu Xia, Zejin Wang, Amit K. Roy-Chowdhury, Jiachen Li
Reinforcement Learning Social Robot Constrained Reinforcement Learning Social Navigation Conformal Regression
Pretrained Visual Representations in Reinforcement Learning
Emlyn Williams, Athanasios Polydoros
Reinforcement Learning Pre Trained Representation Visual Reinforcement Learning
Sublinear Regret for a Class of Continuous-Time Linear--Quadratic Reinforcement Learning Problems
Yilie Huang, Yanwei Jia, Xun Yu Zhou
Reinforcement Learning Optimal Policy Sublinear Regret Actor Critic Algorithm Time Varying Control
Take a Step and Reconsider: Sequence Decoding for Self-Improved Neural Combinatorial Optimization
Jonathan Pirnay, Dominik G. Grimm
Reinforcement Learning Sequence of Sequence Combinatorial Optimization Problem Cross Over Step Neural Combinatorial Optimization
Path Following and Stabilisation of a Bicycle Model using a Reinforcement Learning Approach
Sebastian Weyrer, Peter Manzl, A. L. Schwab, Johannes Gerstmayr
Reinforcement Learning Reinforcement Learning Approach Multibody Dynamic Path Following Self Stabilization Effect Bicycle Model

July 23, 2024

SECRM-2D: RL-Based Efficient and Comfortable Route-Following Autonomous Driving with Analytic Safety Guarantees
Tianyu Shi, Ilia Smirnov, Omar ElSamadisy, Baher Abdulhai
Reinforcement Learning Autonomous Driving Safety Guarantee Unmanned Ground Vehicle Motion Comfort
Adapting Image-based RL Policies via Predicted Rewards
Weiyao Wang, Xinyuan Fang, Gregory D. Hager
Reinforcement Learning Fine Tuning Domain Randomization Reinforcement Learning Policy Reward Prediction Reward Fine Tuning
A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data
Adrian Remonda, Nicklas Hansen, Ayoub Raji, Nicola Musiu, Marko Bertogna, Eduardo Veas, Xiaolong Wang
Reinforcement Learning Autonomous Racing Large Scale Human Autonomous Driving Benchmark
From Imitation to Refinement -- Residual RL for Precise Assembly
Lars Ankile, Anthony Simeonov, Idan Shenfeld, Marcel Torne, Pulkit Agrawal
Reinforcement Learning Fine Tuning Feature Imitation Behavior Cloning Assembly Task Residual Reinforcement Learning Residual Policy
Functional Acceleration for Policy Mirror Descent
Veronica Chelu, Doina Precup
Reinforcement Learning Policy Mirror Descent Policy Parametrization Functional Acceleration
TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback
Eunseop Yoon, Hee Suk Yoon, SooHwan Eom, Gunsoo Han, Daniel Wontae Nam, Daejin Jo, Kyoung-Woon On, Mark A. Hasegawa-Johnson, Sungwoong Kim, Chang D. Yoo
Language Model Reinforcement Learning Fine Grained Human Feedback Preference Label
Reinforcement Learning-based Adaptive Mitigation of Uncorrected DRAM Errors in the Field
Isaac Boixaderas, Sergi Moré, Javier Bartolome, David Vicente, Petar Radojković, Paul M. Carpenter, Eduard Ayguadé
Reinforcement Learning Limited Field Adaptive Method Error Mitigation Random Access Memory Hardware Error Cray XC40 Supercomputer Adaptive Mitigation
Negotiating Control: Neurosymbolic Variable Autonomy
Georgios Bakirtzis, Manolis Chiou, Andreas Theodorou
Reinforcement Learning Mixed Autonomy Autonomous Behavior
ODGR: Online Dynamic Goal Recognition
Matan Shamir, Osher Elhadad, Matthew E. Taylor, Reuth Mirsky
Reinforcement Learning Goal Recognition Dynamic Goal Online Goal Recognition
Automatic Environment Shaping is the Next Frontier in RL
Younghyo Park, Gabriel B. Margolis, Pulkit Agrawal
Reinforcement Learning Reinforcement Learning Algorithm Policy OpTimization Robotic Task New Frontier Unsupervised Environment Design
Diffusion Models as Optimizers for Efficient Planning in Offline RL
Renming Huang, Yunqiang Pei, Guoqing Wang, Yangming Zhang, Yang Yang, Peng Wang, Hengtao Shen
Reinforcement Learning Diffusion Model Better Optimizers Efficient Planning Trajectory Generator

July 22, 2024

Artificial Intelligence-based Decision Support Systems for Precision and Digital Health
Nina Deliu, Bibhas Chakraborty
Reinforcement Learning Synthetic to Real Multidimensional Local Precision Rate Adaptive Intervention Digital Healthcare
Exploring and Addressing Reward Confusion in Offline Preference Learning
Xin Chen, Sam Toyer, Florian Shkurti
Reinforcement Learning Active Learning Spurious Correlation User Preference Offline Preference Reward Ambiguity
Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning
Zhecheng Yuan, Tianming Wei, Shuiqi Cheng, Gu Zhang, Yuanpei Chen, Huazhe Xu
Reinforcement Learning LeArning Abstract Visual Reinforcement Learning Visuo Motor Control Model Generalizability Visual Generalization
Concept-Based Interpretable Reinforcement Learning with Limited to No Human Labels
Zhuorui Ye, Stephanie Milani, Geoffrey J. Gordon, Fei Fang
Reinforcement Learning Concept Bottleneck Model Concept Based Explanation Human Label Interleaved Learning Limited Number

Reinforcement Learning

Papers

SoNIC: Safe Social Navigation with Adaptive Conformal Inference and Constrained Reinforcement Learning

Pretrained Visual Representations in Reinforcement Learning

Sublinear Regret for a Class of Continuous-Time Linear--Quadratic Reinforcement Learning Problems

Take a Step and Reconsider: Sequence Decoding for Self-Improved Neural Combinatorial Optimization

Path Following and Stabilisation of a Bicycle Model using a Reinforcement Learning Approach

SECRM-2D: RL-Based Efficient and Comfortable Route-Following Autonomous Driving with Analytic Safety Guarantees

Adapting Image-based RL Policies via Predicted Rewards

A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data

From Imitation to Refinement -- Residual RL for Precise Assembly

Functional Acceleration for Policy Mirror Descent

TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback

Reinforcement Learning-based Adaptive Mitigation of Uncorrected DRAM Errors in the Field

Negotiating Control: Neurosymbolic Variable Autonomy

ODGR: Online Dynamic Goal Recognition

Automatic Environment Shaping is the Next Frontier in RL

Diffusion Models as Optimizers for Efficient Planning in Offline RL

Artificial Intelligence-based Decision Support Systems for Precision and Digital Health

Exploring and Addressing Reward Confusion in Offline Preference Learning

Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning

Concept-Based Interpretable Reinforcement Learning with Limited to No Human Labels