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

December 24, 2024

Quantum framework for Reinforcement Learning: integrating Markov Decision Process, quantum arithmetic, and trajectory search
Thet Htar Su, Shaswot Shresthamali, Masaaki Kondo
Reinforcement Learning Quantum Computing Quantum Physic Quantum Advantage Quantum Reinforcement Learning Transition Dynamic Trajectory Similarity Quantum Framework Decision Making Process Quantum Search
AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learning
Lixian Jing, Jianpeng Qi, Junyu Dong, Yanwei Yu
Reinforcement Learning Graph Learning Model Pruning DNN Architecture Pruning Framework Automatic Pruning

December 23, 2024

Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning
Orson Mengara
Reinforcement Learning Deep Learning Optimization Purpose Backdoor Attack Bayesian Perspective Data Poisoning Stock Market
HyperQ-Opt: Q-learning for Hyperparameter Optimization
Md. Tarek Hasan
Reinforcement Learning Hyperparameter Optimization Policy Optimization
Reinforcement Learning with a Focus on Adjusting Policies to Reach Targets
Akane Tsuboya, Yu Kono, Tatsuji Takahashi
Reinforcement Learning Deep Reinforcement Learning Environment Exploration Human Driving Focus Policy Design Exploration Method Multiple Target Exploration Efficiency Motion Skill
LMD-PGN: Cross-Modal Knowledge Distillation from First-Person-View Images to Third-Person-View BEV Maps for Universal Point Goal Navigation
Riku Uemura, Kanji Tanaka, Kenta Tsukahara, Daiki Iwata
Reinforcement Learning Bird'S Eye View Navigation Task Cross Modal Knowledge Distillation First Person Mapless Navigation Navigation Model Robot Centric

December 22, 2024

Fairness in Reinforcement Learning with Bisimulation Metrics
Sahand Rezaei-Shoshtari, Hanna Yurchyk, Scott Fujimoto, Doina Precup, David Meger
Reinforcement Learning Procedural Fairness Sequential Decision Bisimulation Metric Long Term Fairness Fairness Benchmark
Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps
Benjamin Ellis, Matthew T. Jackson, Andrei Lupu, Alexander D. Goldie, Mattie Fellows, Shimon Whiteson, Jakob Foerster
Reinforcement Learning Momentum Based Non Stationarity Non Stationary Reinforcement Learning Time Step Adam Algorithm
Environment Descriptions for Usability and Generalisation in Reinforcement Learning
Dennis J.N.J. Soemers, Spyridon Samothrakis, Kurt Driessens, Mark H.M. Winands
Reinforcement Learning Strong Generalization Environment Feature Unseen Environment Important Usability Challenge Wilderness Search Text Based Environment Current Reinforcement Learning
Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model
Songjun Tu, Jingbo Sun, Qichao Zhang, Xiangyuan Lan, Dongbin Zhao
Large Language Model Language Model Reinforcement Learning Human Feedback Preference Feedback LLM Generated Online Service
ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning
Kun Wu, Yinuo Zhao, Zhiyuan Xu, Zhengping Che, Chengxiang Yin, Chi Harold Liu, Qinru Qiu, Feiferi Feng, Jian Tang
Reinforcement Learning Offline Reinforcement Learning Q Learning Action Free Offline Q Value Adaptive Weight ACL2 Proof Debugging Tool
Online Learning from Strategic Human Feedback in LLM Fine-Tuning
Shugang Hao, Lingjie Duan
Reinforcement Learning Human Feedback Online Learning LLM Fine Tuning Bayesian Game Human Labelers

December 21, 2024

Subgoal Discovery Using a Free Energy Paradigm and State Aggregations
Amirhossein Mesbah, Reshad Hosseini, Seyed Pooya Shariatpanahi, Majid Nili Ahmadabadi
Reinforcement Learning Free Energy Goal Conditioned Reinforcement Learning Task Decomposition Subgoal Search
On Enhancing Network Throughput using Reinforcement Learning in Sliced Testbeds
Daniel Pereira Monteiro, Lucas Nardelli de Freitas Botelho Saar, Larissa Ferreira Rodrigues Moreira, Rodrigo Moreira
Reinforcement Learning Deep Q Network Test Bed Worst Case User Throughput Network Slicing Model Slicing Slice by Slice

December 20, 2024

Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planning
Rashmeet Kaur Nayyar, Siddharth Srivastava
Reinforcement Learning LeArning Abstract Task Planning Hierarchical Reinforcement Learning Action Representation Abstract Concept Generalizable Approach Autonomous Stock Trading
Multi Agent Reinforcement Learning for Sequential Satellite Assignment Problems
Joshua Holder, Natasha Jaques, Mehran Mesbahi
Reinforcement Learning Multi Agent Reinforcement Learning Related Problem Optimal Assignment Satellite Scheduling
VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving
Zilin Huang, Zihao Sheng, Yansong Qu, Junwei You, Sikai Chen
Reinforcement Learning Autonomous Driving New Framework Reward Signal Safe Autonomous Driving
SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch
Shengyu Feng, Yiming Yang
Reinforcement Learning LeArning Abstract Specific Heuristic Multi Channel Branch
Generalized Back-Stepping Experience Replay in Sparse-Reward Environments
Guwen Lyu, Masahiro Sato
Reinforcement Learning Environment Feature Experience Replay Sparse Reward Environment Dense Reward
Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning
Yangkun Chen, Kai Yang, Jian Tao, Jiafei Lyu
Reinforcement Learning Agent Behavior Data Recycling Independent Sampling Random Network Distillation

Reinforcement Learning

Papers

Quantum framework for Reinforcement Learning: integrating Markov Decision Process, quantum arithmetic, and trajectory search

AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learning

Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning

HyperQ-Opt: Q-learning for Hyperparameter Optimization

Reinforcement Learning with a Focus on Adjusting Policies to Reach Targets

LMD-PGN: Cross-Modal Knowledge Distillation from First-Person-View Images to Third-Person-View BEV Maps for Universal Point Goal Navigation

Fairness in Reinforcement Learning with Bisimulation Metrics

Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps

Environment Descriptions for Usability and Generalisation in Reinforcement Learning

Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model

ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning

Online Learning from Strategic Human Feedback in LLM Fine-Tuning

Subgoal Discovery Using a Free Energy Paradigm and State Aggregations

On Enhancing Network Throughput using Reinforcement Learning in Sliced Testbeds

Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planning

Multi Agent Reinforcement Learning for Sequential Satellite Assignment Problems

VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving

SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch

Generalized Back-Stepping Experience Replay in Sparse-Reward Environments

Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning