Single Agent Reinforcement Learning

Single-agent reinforcement learning (RL) focuses on training a single agent to learn optimal actions within an environment to maximize cumulative rewards. Current research emphasizes improving sample efficiency, particularly through techniques like higher replay ratios and decoupling exploration and exploitation, often employing deep Q-learning or actor-critic methods. These advancements are significant because they enable more efficient training of RL agents for complex tasks, with applications ranging from robotics and autonomous vehicles to resource allocation in power grids and communication networks.

Papers

November 1, 2024

Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayesian Theory
Zhi Zhang, Chris Chow, Yasi Zhang, Yanchao Sun, Haochen Zhang, Eric Hanchen Jiang, Han Liu, Furong Huang, Yuchen Cui, Oscar Hernan Madrid Padilla
PAC Bayesian Single Agent Reinforcement Learning Statistical Guarantee Lifelong Reinforcement Learning Policy Distribution

October 23, 2024

Bridging Swarm Intelligence and Reinforcement Learning
Karthik Soma, Yann Bouteiller, Heiko Hamann, Giovanni Beltrame
Reinforcement Learning Multi Armed Bandit Swarm Intelligence Single Agent Reinforcement Learning Collective Decision Making Evolutionary Game Theory

October 3, 2024

Learning Emergence of Interaction Patterns across Independent RL Agents in Multi-Agent Environments
Vasanth Reddy Baddam, Suat Gumussoy, Almuatazbellah Boker, Hoda Eldardiry
Multi Agent Reinforcement Learning Multi Agent Multi Agent Environment Single Agent Reinforcement Learning interactiOn Pattern Independent Q Learning Emergent Intelligence

September 25, 2024

Asynchronous Fractional Multi-Agent Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing
Lyudong Jin, Ming Tang, Jiayu Pan, Meng Zhang, Hao Wang
Multi Agent Reinforcement Learning Multi Agent Deep Reinforcement Learning Mobile Edge Computing Single Agent Reinforcement Learning Fractional Derivative Neural Fractional

September 24, 2024

Bridging Environments and Language with Rendering Functions and Vision-Language Models
Theo Cachet, Christopher R. Dance, Olivier Sigaud
Reinforcement Learning Vision Language Model Multi Task Human Language Simple Function Bridging Text Language Conditioned Single Agent Reinforcement Learning

August 25, 2024

MASQ: Multi-Agent Reinforcement Learning for Single Quadruped Robot Locomotion
Qi Liu, Jingxiang Guo, Sixu Lin, Shuaikang Ma, Jinxuan Zhu, Yanjie Li
Multi Agent Reinforcement Learning Multi Agent Deep Reinforcement Learning Quadrupedal Locomotion Single Agent Reinforcement Learning Locomotion Policy

May 23, 2024

A finite time analysis of distributed Q-learning
Han-Dong Lim, Donghwan Lee
Multi Agent Reinforcement Learning Q Learning Sequential Decision Making Problem Finite Time Single Agent Reinforcement Learning

April 28, 2024

Using Deep Q-Learning to Dynamically Toggle between Push/Pull Actions in Computational Trust Mechanisms
Zoi Lygizou, Dimitris Kalles
Deep Q Learning Single Agent Reinforcement Learning Adaptive Agent UNO Push Push Pull Open Multi Agent System

April 15, 2024

Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning
Linjie Xu, Zichuan Liu, Alexander Dockhorn, Diego Perez-Liebana, Jinyu Wang, Lei Song, Jiang Bian
Reinforcement Learning Multi Agent Reinforcement Learning Single Agent Reinforcement Learning Episodic Training Efficient Generated Object Replay

February 29, 2024

ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
Yifei Zhou, Andrea Zanette, Jiayi Pan, Sergey Levine, Aviral Kumar
Large Language Model Reinforcement Learning Policy Reinforcement Learning Single Agent Reinforcement Learning Language Model Agent

February 26, 2024

Reinforcement Learning Based Oscillation Dampening: Scaling up Single-Agent RL algorithms to a 100 AV highway field operational test
Kathy Jang, Nathan Lichtlé, Eugene Vinitsky, Adit Shah, Matthew Bunting, Matthew Nice, Benedetto Piccoli, Benjamin Seibold, Daniel B. Work, Maria Laura Delle Monache, Jonathan Sprinkle, Jonathan W. Lee, Alexandre M. Bayen
Reinforcement Learning Deep Reinforcement Learning Autonomous Driving Reinforcement Learning Algorithm Level Test Single Agent Reinforcement Learning Self Driving Car

February 8, 2024

Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL
Jiawei Huang, Niao He, Andreas Krause
Reinforcement Learning Nash Equilibrium Mean Field Markov Game Mean Field Game Single Agent Reinforcement Learning

December 26, 2023

Efficient Reinforcement Learning via Decoupling Exploration and Utilization
Jingpu Yang, Helin Wang, Qirui Zhao, Zhecheng Shi, Zirui Song, Miao Fang
Reinforcement Learning Efficient Reinforcement Learning Multi Agent Decoupling Coefficient Single Agent Reinforcement Learning Resource Utilization Optimistic Exploration Reinforcement Learning Paradigm

December 19, 2023

Curriculum Learning for Cooperation in Multi-Agent Reinforcement Learning
Rupali Bhati, Sai Krishna Gottipati, Clodéric Mars, Matthew E. Taylor
Multi Agent Reinforcement Learning Curriculum Learning Long Term Cooperation Intelligent Agent Single Agent Reinforcement Learning Multi Agent Setting Training Agent Unknown Teammate

November 10, 2023

Multi-Agent Reinforcement Learning for the Low-Level Control of a Quadrotor UAV
Beomyeol Yu, Taeyoung Lee
Multi Agent Reinforcement Learning Single Agent Single Agent Reinforcement Learning Quadrotor UAV Quadrotor Control Quadrotor Dynamic Low Level

November 3, 2023

Towards model-free RL algorithms that scale well with unstructured data
Joseph Modayil, Zaheer Abbas
Reinforcement Learning Reward Function Reinforcement Learning Algorithm Unstructured Data Model Free Reinforcement Learning Deep RL Single Agent Reinforcement Learning

October 31, 2023

Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning
Sleiman Safaoui, Abraham P. Vinod, Ankush Chakrabarty, Rien Quirynen, Nobuyuki Yoshikawa, Stefano Di Cairano
Reinforcement Learning Motion Planning High Uncertainty Anticipation Single Drone Trajectory Planning Single Agent Reinforcement Learning

October 23, 2023

October 4, 2023

Multi-Agent Reinforcement Learning for Power Grid Topology Optimization
Erica van der Sar, Alessandro Zocca, Sandjai Bhulai
Reinforcement Learning Multi Agent Reinforcement Learning Action Space Power Grid Single Agent Reinforcement Learning Topology Control

Single Agent Reinforcement Learning

Papers

Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayesian Theory

Bridging Swarm Intelligence and Reinforcement Learning

Learning Emergence of Interaction Patterns across Independent RL Agents in Multi-Agent Environments

Asynchronous Fractional Multi-Agent Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing

Bridging Environments and Language with Rendering Functions and Vision-Language Models

MASQ: Multi-Agent Reinforcement Learning for Single Quadruped Robot Locomotion

A finite time analysis of distributed Q-learning

Using Deep Q-Learning to Dynamically Toggle between Push/Pull Actions in Computational Trust Mechanisms

Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning

ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL

Reinforcement Learning Based Oscillation Dampening: Scaling up Single-Agent RL algorithms to a 100 AV highway field operational test

Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL

Efficient Reinforcement Learning via Decoupling Exploration and Utilization

Curriculum Learning for Cooperation in Multi-Agent Reinforcement Learning

Multi-Agent Reinforcement Learning for the Low-Level Control of a Quadrotor UAV

Towards model-free RL algorithms that scale well with unstructured data

Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning

Enhancing Robotic Manipulation: Harnessing the Power of Multi-Task Reinforcement Learning and Single Life Reinforcement Learning in Meta-World

Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization

Multi-Agent Reinforcement Learning for Power Grid Topology Optimization