Ensemble Deep Reinforcement Learning

Ensemble deep reinforcement learning (EDRL) combines multiple deep reinforcement learning models to improve the robustness, efficiency, and generalization of decision-making agents. Current research focuses on enhancing exploration strategies within ensembles, developing hybrid approaches that integrate EDRL with other control methods (e.g., model predictive control), and optimizing ensemble training through techniques like hierarchical learning and efficient sampling methods. EDRL's ability to improve performance and sample efficiency across diverse applications, including healthcare (artificial pancreas), transportation (traffic signal control), and robotics, makes it a significant area of ongoing research with substantial practical implications.

Papers

October 17, 2023

Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control
Chao Li, Chen Gong, Qiang He, Xinwen Hou
Deep Reinforcement Learning Environment Exploration Continuous Control Ensemble Deep Reinforcement Learning Model Trajectory

July 13, 2023

Hybrid Control Policy for Artificial Pancreas via Ensemble Deep Reinforcement Learning
Wenzhou Lv, Tianyu Wu, Luolin Xiong, Liang Wu, Jian Zhou, Yang Tang, Feng Qian
Type 2 Diabetes Hybrid Control Artificial Pancreas Ensemble Deep Reinforcement Learning

March 15, 2023

Optimal Energy Management of Plug-in Hybrid Vehicles Through Exploration-to-Exploitation Ratio Control in Ensemble Reinforcement Learning
Bin Shuai, Min Hua, Yanfei Li, Shijin Shuai, Hongming Xu, Quan Zhou
Reinforcement Learning Energy Management Exploration Exploitation Trade Ensemble Deep Reinforcement Learning Hybrid Electric Vehicle Vehicle Energy

March 5, 2023

Ensemble Reinforcement Learning: A Survey
Yanjie Song, P. N. Suganthan, Witold Pedrycz, Junwei Ou, Yongming He, Yingwu Chen, Yutong Wu
Reinforcement Learning Timely Survey Ensemble Learning Model Selection Ensemble Deep Reinforcement Learning

January 16, 2023

PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination
Xingzhou Lou, Jiaxian Guo, Junge Zhang, Jun Wang, Kaiqi Huang, Yali Du
Content Addressable Memory Zero Shot Coordination Human AI Coordination Ensemble Deep Reinforcement Learning

September 29, 2022

Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training
Gang Chen, Victoria Huang
Reinforcement Learning Deep Reinforcement Learning Actor Critic Multi Step Based Policy Continuous Space Ensemble Algorithm Ensemble Deep Reinforcement Learning

June 9, 2022

An Optimization Method-Assisted Ensemble Deep Reinforcement Learning Algorithm to Solve Unit Commitment Problems
Jingtao Qin, Yuanqi Gao, Mikhail Bragin, Nanpeng Yu
Reinforcement Learning Unit Commitment Ensemble Deep Reinforcement Learning

May 27, 2022

Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters
Seyed Kamyar Seyed Ghasemipour, Shixiang Shane Gu, Ofir Nachum
Offline Reinforcement Learning Diverse Ensemble High Uncertainty Value Local Independence Efficient Uncertainty Estimation Ensemble Deep Reinforcement Learning

May 19, 2022

Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble
Zhengyu Yang, Kan Ren, Xufang Luo, Minghuan Liu, Weiqing Liu, Jiang Bian, Weinan Zhang, Dongsheng Li
Reinforcement Learning Strong Generalization Proximal Policy Optimization Sample Efficiency Ensemble Deep Reinforcement Learning Vanilla Reinforcement Learning

April 7, 2022

Hybrid LMC: Hybrid Learning and Model-based Control for Wheeled Humanoid Robot via Ensemble Deep Reinforcement Learning
Donghoon Baek, Amartya Purushottam, Joao Ramos
Reinforcement Learning Model Based Hybrid Learning Ensemble Deep Reinforcement Learning Wheeled Humanoid

March 10, 2022

Random Ensemble Reinforcement Learning for Traffic Signal Control
Ruijie Qi, Jianbin Huang, He Li, Qinglin Tan, Longji Huang, Jiangtao Cui
Traffic Signal Control Ensemble Deep Reinforcement Learning Double DQN

January 31, 2022

DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning
Hassam Sheikh, Kizza Frisbee, Mariano Phielipp
Back Propagation Determinantal Point Process Neural Point Process Ensemble Deep Reinforcement Learning

Ensemble Deep Reinforcement Learning

Papers

Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control

Hybrid Control Policy for Artificial Pancreas via Ensemble Deep Reinforcement Learning

Optimal Energy Management of Plug-in Hybrid Vehicles Through Exploration-to-Exploitation Ratio Control in Ensemble Reinforcement Learning

Ensemble Reinforcement Learning: A Survey

PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination

Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training

An Optimization Method-Assisted Ensemble Deep Reinforcement Learning Algorithm to Solve Unit Commitment Problems

Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters

Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble

Hybrid LMC: Hybrid Learning and Model-based Control for Wheeled Humanoid Robot via Ensemble Deep Reinforcement Learning

Random Ensemble Reinforcement Learning for Traffic Signal Control

DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning