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

September 26, 2023

Less Is More: Robust Robot Learning via Partially Observable Multi-Agent Reinforcement Learning
Wenshuai Zhao, Eetu-Aleksi Rantala, Joni Pajarinen, Jorge Peña Queralta
Multi Agent Reinforcement Learning Single Agent Reinforcement Learning Multi Agent Task Robust Robot

September 20, 2023

Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learning
Jingkai Sun, Qiang Zhang, Yiqun Duan, Xiaoyang Jiang, Chong Cheng, Renjing Xu
Reinforcement Learning Imitation Learning Humanoid Robot Style PROMPT High Level Plan Single Agent Reinforcement Learning Adversarial Imitation Humanoid Control

August 17, 2023

Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
Songtao Feng, Ming Yin, Yu-Xiang Wang, Jing Yang, Yingbin Liang
Multi Agent Reinforcement Learning Model Free Reinforcement Learning Markov Game Sample Efficiency Episodic Markov Decision Process Single Agent Reinforcement Learning Zero Sum Markov Game Model Free Algorithm

July 25, 2023

Communication-Efficient Orchestrations for URLLC Service via Hierarchical Reinforcement Learning
Wei Shi, Milad Ganjalizadeh, Hossein Shokri Ghadikolaei, Marina Petrova
Reinforcement Learning Multi Agent Reinforcement Learning Hierarchical Reinforcement Learning Single Agent Reinforcement Learning Ultra Reliable Low Latency Communication Kernel Orchestration

July 12, 2023

Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior
Kai Cui, Sascha Hauck, Christian Fabian, Heinz Koeppl
LeArning Abstract Multi Agent Reinforcement Learning Mean Field Single Agent Single Agent Reinforcement Learning

April 13, 2023

Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning
Wenli Xiao, Yiwei Lyu, John Dolan
Multi Agent Reinforcement Learning Temporal Logic Multi Agent Environment Single Agent Reinforcement Learning Multi Agent Scenario Model Based Shielding

March 30, 2023

When Learning Is Out of Reach, Reset: Generalization in Autonomous Visuomotor Reinforcement Learning
Zichen Zhang, Luca Weihs
Reinforcement Learning LeArning Abstract Strong Generalization Single Agent Reinforcement Learning Aim 2 Global Reset Feature Episodic Training Reset Free

January 31, 2023

Scaling laws for single-agent reinforcement learning
Jacob Hilton, Jie Tang, John Schulman
Generative Modeling Cross Entropy Loss Model Size Single Agent Reinforcement Learning Intrinsic Evaluation

January 3, 2023

A Succinct Summary of Reinforcement Learning
Sanjeevan Ahilan
Reinforcement Learning Structured Summary Key Result Single Agent Reinforcement Learning Specific Audience

November 3, 2022

Theta-Resonance: A Single-Step Reinforcement Learning Method for Design Space Exploration
Masood S. Mortazavi, Tiancheng Qin, Ning Yan
Deep Reinforcement Learning Policy Gradient Design Space Single Agent Reinforcement Learning Design Space Exploration Theta to Alpha

October 31, 2022

Agent-Time Attention for Sparse Rewards Multi-Agent Reinforcement Learning
Jennifer She, Jayesh K. Gupta, Mykel J. Kochenderfer
Multi Agent Reinforcement Learning Sparse Reward Single Agent Reinforcement Learning

October 29, 2022

LearningGroup: A Real-Time Sparse Training on FPGA via Learnable Weight Grouping for Multi-Agent Reinforcement Learning
Je Yang, JaeUk Kim, Joo-Young Kim
Multi Agent Reinforcement Learning Field Programmable Gate Array Single Agent Reinforcement Learning Weight Freezing Dynamic Sparse Training Group Learning Better on Chip Data Sparse Accelerator

October 17, 2022

You Only Live Once: Single-Life Reinforcement Learning
Annie S. Chen, Archit Sharma, Sergey Levine, Chelsea Finn
Disaster Response Single Agent Reinforcement Learning Episodic Reinforcement Learning

October 13, 2022

Multi-agent Dynamic Algorithm Configuration
Ke Xue, Jiacheng Xu, Lei Yuan, Miqing Li, Chao Qian, Zongzhang Zhang, Yang Yu
Reinforcement Learning Single Agent Reinforcement Learning Contextual Markov Decision Process

September 15, 2022

Scalable Task-Driven Robotic Swarm Control via Collision Avoidance and Learning Mean-Field Control
Kai Cui, Mengguang Li, Christian Fabian, Heinz Koeppl
Multi Agent Reinforcement Learning Collision Avoidance Mean Field Single Agent Reinforcement Learning Classical Control Swarm Navigation

July 25, 2022

Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions
Shuang Qiu, Xiaohan Wei, Jieping Ye, Zhaoran Wang, Zhuoran Yang
Markov Game Single Agent Reinforcement Learning Zero Sum Markov Game State Transition Two Agent Fictitious Play

July 4, 2022

Goal-Conditioned Generators of Deep Policies
Francesco Faccio, Vincent Herrmann, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber
Goal Conditioned Reinforcement Learning Single Agent Reinforcement Learning Neural Network Policy Deep Policy Expressive Policy Conditioned Generation

June 25, 2022

Hierarchical Reinforcement Learning with Opponent Modeling for Distributed Multi-agent Cooperation
Zhixuan Liang, Jiannong Cao, Shan Jiang, Divya Saxena, Huafeng Xu
Deep Reinforcement Learning Hierarchical Reinforcement Learning Single Agent Reinforcement Learning Multi Agent Cooperation Opponent Modeling

May 27, 2022

Deep Reinforcement Learning for Distributed and Uncoordinated Cognitive Radios Resource Allocation
Ankita Tondwalkar, Andres Kwasinski
Deep Reinforcement Learning Q Learning Resource Allocation Single Agent Reinforcement Learning Cognitive Radio Clean Distribution Learning Based Resource Allocation

May 11, 2022

Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learning
Shuhan Qi, Shuhao Zhang, Xiaohan Hou, Jiajia Zhang, Xuan Wang, Jing Xiao
New Framework High Efficiency Multi Agent Reinforcement Learning Single Agent Reinforcement Learning MARL Algorithm Real Time Strategy

Single Agent Reinforcement Learning

Papers

Less Is More: Robust Robot Learning via Partially Observable Multi-Agent Reinforcement Learning

Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learning

Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games

Communication-Efficient Orchestrations for URLLC Service via Hierarchical Reinforcement Learning

Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior

Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning

When Learning Is Out of Reach, Reset: Generalization in Autonomous Visuomotor Reinforcement Learning

Scaling laws for single-agent reinforcement learning

A Succinct Summary of Reinforcement Learning

Theta-Resonance: A Single-Step Reinforcement Learning Method for Design Space Exploration

Agent-Time Attention for Sparse Rewards Multi-Agent Reinforcement Learning

LearningGroup: A Real-Time Sparse Training on FPGA via Learnable Weight Grouping for Multi-Agent Reinforcement Learning

You Only Live Once: Single-Life Reinforcement Learning

Multi-agent Dynamic Algorithm Configuration

Scalable Task-Driven Robotic Swarm Control via Collision Avoidance and Learning Mean-Field Control

Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions

Goal-Conditioned Generators of Deep Policies

Hierarchical Reinforcement Learning with Opponent Modeling for Distributed Multi-agent Cooperation

Deep Reinforcement Learning for Distributed and Uncoordinated Cognitive Radios Resource Allocation

Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learning