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

November 8, 2024

Reinforcement Learning for Adaptive Resource Scheduling in Complex System Environments
Pochun Li, Yuyang Xiao, Jinghua Yan, Xuan Li, Xiaoye Wang
Reinforcement Learning Q Learning Resource Allocation Complexity Level Dynamic Scheduling
Improving Multi-Domain Task-Oriented Dialogue System with Offline Reinforcement Learning
Dharmendra Prajapat, Durga Toshniwal
Language Model Reinforcement Learning Pre Trained Language Model Dialogue System Task Oriented Action Free Offline

November 7, 2024

Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations
Joey Hong, Jessica Lin, Anca Dragan, Sergey Levine
Reinforcement Learning Dialogue Agent Hindsight Instruction
Inverse Transition Learning: Learning Dynamics from Demonstrations
Leo Benac, Abhishek Sharma, Sonali Parbhoo, Finale Doshi-Velez
Reinforcement Learning Inverse Reinforcement Learning Noisy Demonstration Learning Dynamic Constraint Programming Expert Trajectory Transition Dynamic
Noisy Zero-Shot Coordination: Breaking The Common Knowledge Assumption In Zero-Shot Coordination Games
Usman Anwar, Ashish Pandian, Jia Wan, David Krueger, Jakob Foerster
Reinforcement Learning Zero Shot Coordination
Think Smart, Act SMARL! Analyzing Probabilistic Logic Driven Safety in Multi-Agent Reinforcement Learning
Satchit Chatterji, Erman Acar
Reinforcement Learning Multi Agent Reinforcement Learning Policy Gradient Q Learning Safety Guarantee Multi Agent Reinforcement Safe Multi Agent Reinforcement Learning Model Based Safe Reinforcement Learning
Navigating Trade-offs: Policy Summarization for Multi-Objective Reinforcement Learning
Zuzanna Osika, Jazmin Zatarain-Salazar, Frans A. Oliehoek, Pradeep K. Murukannaiah
Reinforcement Learning Reward Function Multi Objective Multi Objective Reinforcement Learning Multiple Objective Objective Space
Semantic-Aware Resource Management for C-V2X Platooning via Multi-Agent Reinforcement Learning
Zhiyu Shao, Qiong Wu, Pingyi Fan, Kezhi Wang, Qiang Fan, Wen Chen, Khaled B. Letaief
Reinforcement Learning Multi Agent Reinforcement Learning Platoon Control Resource Management Multimodal Semantic Vehicle to Everything C V2x
Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
Heyang Zhao, Chenlu Ye, Quanquan Gu, Tong Zhang
Reinforcement Learning Contextual Bandit Reinforcement Learning From Human Feedback Kullback Leibler
Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning
Marvin Alles, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl
Reinforcement Learning LeArning Abstract Offline Reinforcement Learning Model Based Offline Reinforcement Learning Latent Action Latent Action Space
Deep Heuristic Learning for Real-Time Urban Pathfinding
Mohamed Hussein Abo El-Ela, Ali Hamdi Fergany
Reinforcement Learning Deep Learning Deep Learning Model Optimal Path

November 6, 2024

Learning Generalizable Policy for Obstacle-Aware Autonomous Drone Racing
Yueqian Liu
Reinforcement Learning Obstacle Free
Approximate Equivariance in Reinforcement Learning
Jung Yeon Park, Sujay Bhatt, Sihan Zeng, Lawson L.S. Wong, Alec Koppel, Sumitra Ganesh, Robin Walters
Reinforcement Learning Inter Part Equivariance Approximate Symmetry Equivariant Network Equivariant Neural Network Approximate Transformation Invariance
A Comparative Study of Deep Reinforcement Learning for Crop Production Management
Joseph Balderas, Dong Chen, Yanbo Huang, Li Wang, Ren-Cang Li
Reinforcement Learning Deep Reinforcement Learning Comparative Study Crop Breeding Crop Simulation
Interpretable and Efficient Data-driven Discovery and Control of Distributed Systems
Florian Wolf, Nicolò Botteghi, Urban Fasel, Andrea Manzoni
Reinforcement Learning External Control Nonlinear Dynamic Data Driven Discovery PDE Control Control Paradigm
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
Alexandre Galashov, Michalis K. Titsias, András György, Clare Lyle, Razvan Pascanu, Yee Whye Teh, Maneesh Sahani
Reinforcement Learning Neural Network Continual LEArning Non Stationary Global Reset Feature Drift Adaptation
AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making
Yizhe Huang, Xingbo Wang, Hao Liu, Fanqi Kong, Aoyang Qin, Min Tang, Xiaoxi Wang, Song-Chun Zhu, Mingjie Bi, Siyuan Qi, Xue Feng
Reinforcement Learning Single Agent Multi Agent Environment Multi Agent Setting Multi Agent Decision
Beyond The Rainbow: High Performance Deep Reinforcement Learning On A Desktop PC
Tyler Clark, Mark Towers, Christine Evers, Jonathon Hare
Reinforcement Learning Deep Q Network Digital Computer ATARI Game
From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning
Zhirui Deng, Zhicheng Dou, Yutao Zhu, Ji-Rong Wen, Ruibin Xiong, Mang Wang, Weipeng Chen
Reinforcement Learning Expert Knowledge Inverse Reinforcement Learning Sample STEP Implicit Reward Novice Classification
Opportunities of Reinforcement Learning in South Africa's Just Transition
Claude Formanek, Callum Rhys Tilbury, Jonathan P. Shock
Reinforcement Learning Emerging Opportunity Late Time Transition Community Resilience Industrial Revolution Socioeconomic Prediction

Reinforcement Learning

Papers

Reinforcement Learning for Adaptive Resource Scheduling in Complex System Environments

Improving Multi-Domain Task-Oriented Dialogue System with Offline Reinforcement Learning

Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations

Inverse Transition Learning: Learning Dynamics from Demonstrations

Noisy Zero-Shot Coordination: Breaking The Common Knowledge Assumption In Zero-Shot Coordination Games

Think Smart, Act SMARL! Analyzing Probabilistic Logic Driven Safety in Multi-Agent Reinforcement Learning

Navigating Trade-offs: Policy Summarization for Multi-Objective Reinforcement Learning

Semantic-Aware Resource Management for C-V2X Platooning via Multi-Agent Reinforcement Learning

Sharp Analysis for KL-Regularized Contextual Bandits and RLHF

Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning

Deep Heuristic Learning for Real-Time Urban Pathfinding

Learning Generalizable Policy for Obstacle-Aware Autonomous Drone Racing

Approximate Equivariance in Reinforcement Learning

A Comparative Study of Deep Reinforcement Learning for Crop Production Management

Interpretable and Efficient Data-driven Discovery and Control of Distributed Systems

Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset

AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making

Beyond The Rainbow: High Performance Deep Reinforcement Learning On A Desktop PC

From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning

Opportunities of Reinforcement Learning in South Africa's Just Transition