Efficient Reinforcement Learning

Efficient reinforcement learning (RL) aims to accelerate the training of RL agents by reducing the computational cost and data requirements, enabling application to complex real-world problems. Current research focuses on improving sample efficiency through techniques like reward shaping with large language models, physics-informed models, action space reduction, and leveraging offline datasets or expert demonstrations. These advancements, often implemented using model-based RL, policy gradient methods, or actor-critic architectures, are crucial for deploying RL in resource-constrained settings and high-dimensional problems such as robotics and autonomous driving, ultimately bridging the gap between theoretical advancements and practical applications.

Papers

December 16, 2023

Deriving Rewards for Reinforcement Learning from Symbolic Behaviour Descriptions of Bipedal Walking
Daniel Harnack, Christoph Lüth, Lukas Gross, Shivesh Kumar, Frank Kirchner
Reinforcement Learning Reward Function Efficient Reinforcement Learning Reward Structure Symbolic AI Hybrid Automaton

December 2, 2023

A Multifidelity Sim-to-Real Pipeline for Verifiable and Compositional Reinforcement Learning
Cyrus Neary, Christian Ellis, Aryaman Singh Samyal, Craig Lennon, Ufuk Topcu
Reinforcement Learning Efficient Reinforcement Learning Compositional Reinforcement Learning

November 7, 2023

Time-Efficient Reinforcement Learning with Stochastic Stateful Policies
Firas Al-Hafez, Guoping Zhao, Jan Peters, Davide Tateo
Reinforcement Learning Policy Gradient Efficient Reinforcement Learning Stochastic Policy Deep Policy

October 25, 2023

Model predictive control-based value estimation for efficient reinforcement learning
Qizhen Wu, Kexin Liu, Lei Chen
Reinforcement Learning Full Model Predictive Control Obstacle Avoidance Efficient Reinforcement Learning Learned Environment Model

October 18, 2023

Accelerate Presolve in Large-Scale Linear Programming via Reinforcement Learning
Yufei Kuang, Xijun Li, Jie Wang, Fangzhou Zhu, Meng Lu, Zhihai Wang, Jia Zeng, Houqiang Li, Yongdong Zhang, Feng Wu
Reinforcement Learning Efficient Reinforcement Learning Automatic Solver Programming Solver Fast Solver Large Scale Linear Programming

October 17, 2023

Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach
Dengwang Tang, Rahul Jain, Botao Hao, Zheng Wen
Optimal Policy Online Learning Efficient Reinforcement Learning Bayesian Approach Cumulative Regret Offline Data Infinite Horizon Prior Dependent

October 16, 2023

ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
Ziniu Li, Tian Xu, Yushun Zhang, Zhihang Lin, Yang Yu, Ruoyu Sun, Zhi-Quan Luo
Reinforcement Learning Proximal Policy Optimization Efficient Reinforcement Learning Many Property

September 13, 2023

Efficient Reinforcement Learning for Jumping Monopods
Riccardo Bussola, Michele Focchi, Andrea Del Prete, Daniele Fontanelli, Luigi Palopoli
Reinforcement Learning Efficient Reinforcement Learning Low Level Quadrupedal Jumping Loop Optimal Control

September 5, 2023

Efficient RL via Disentangled Environment and Agent Representations
Kevin Gmelin, Shikhar Bahl, Russell Mendonca, Deepak Pathak
Environment Feature Structured Representation Efficient Reinforcement Learning Visual Knowledge Effective Representation Agent Representation

August 4, 2023

Learning Optimal Admission Control in Partially Observable Queueing Networks
Jonatha Anselmi, Bruno Gaujal, Louis-Sébastien Rebuffi
Reinforcement Learning Markov Decision Process Efficient Reinforcement Learning Admission Control

July 6, 2023

A Neuromorphic Architecture for Reinforcement Learning from Real-Valued Observations
Sergio F. Chevtchenko, Yeshwanth Bethi, Teresa B. Ludermir, Saeed Afshar
Reinforcement Learning Spiking Neural Network Proximal Policy Optimization Actor Critic Algorithm Efficient Reinforcement Learning Real Data Neuromorphic Architecture

June 28, 2023

Structure in Deep Reinforcement Learning: A Survey and Open Problems
Aditya Mohan, Amy Zhang, Marius Lindauer
Reinforcement Learning Timely Survey Deep Reinforcement Learning Inner Structure Efficient Reinforcement Learning Open Problem

June 22, 2023

Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping
Yining Li, Peizhong Ju, Ness Shroff
Reinforcement Learning Action Space Efficient Reinforcement Learning Optimal Grouping

June 11, 2023

Learning World Models with Identifiable Factorization
Yu-Ren Liu, Biwei Huang, Zhengmao Zhu, Honglong Tian, Mingming Gong, Yang Yu, Kun Zhang
Ground Truth Policy OpTimization World Model Policy Learning Efficient Reinforcement Learning

June 2, 2023

Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations
Minshuo Chen, Jie Meng, Yu Bai, Yinyu Ye, H. Vincent Poor, Mengdi Wang
LeArning Abstract Optimal Regret Efficient Reinforcement Learning Full Observability Real World Reinforcement Learning Significant Delay Change

May 25, 2023

Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks
Honghao Wei, Xin Liu, Weina Wang, Lei Ying
Financial Application Network Programming Deep Q Learning Efficient Reinforcement Learning Sample Efficient Reinforcement Learning Hybrid System Augmented Sample Pseudo Stochastic

May 8, 2023

Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors
Letian Wang, Jie Liu, Hao Shao, Wenshuo Wang, Ruobing Chen, Yu Liu, Steven L. Waslander
Reinforcement Learning Autonomous Driving Autonomous Vehicle Efficient Reinforcement Learning SAM Prior Parameterized Skill

April 29, 2023

Semi-Infinitely Constrained Markov Decision Processes and Efficient Reinforcement Learning
Liangyu Zhang, Yang Peng, Wenhao Yang, Zhihua Zhang
Model Based Reinforcement Learning Efficient Reinforcement Learning Constrained Markov Decision Process

April 25, 2023

What can online reinforcement learning with function approximation benefit from general coverage conditions?
Fanghui Liu, Luca Viano, Volkan Cevher
Reinforcement Learning Online Reinforcement Learning Sample Efficient Function Approximation Efficient Reinforcement Learning Higher Coverage Rate Linear MDPs

March 7, 2023

A Multiplicative Value Function for Safe and Efficient Reinforcement Learning
Nick Bührer, Zhejun Zhang, Alexander Liniger, Fisher Yu, Luc Van Gool
Proximal Policy Optimization Safe Reinforcement Learning Value Function Efficient Reinforcement Learning Reward Learning

Efficient Reinforcement Learning

Papers

Deriving Rewards for Reinforcement Learning from Symbolic Behaviour Descriptions of Bipedal Walking

A Multifidelity Sim-to-Real Pipeline for Verifiable and Compositional Reinforcement Learning

Time-Efficient Reinforcement Learning with Stochastic Stateful Policies

Model predictive control-based value estimation for efficient reinforcement learning

Accelerate Presolve in Large-Scale Linear Programming via Reinforcement Learning

Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach

ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models

Efficient Reinforcement Learning for Jumping Monopods

Efficient RL via Disentangled Environment and Agent Representations

Learning Optimal Admission Control in Partially Observable Queueing Networks

A Neuromorphic Architecture for Reinforcement Learning from Real-Valued Observations

Structure in Deep Reinforcement Learning: A Survey and Open Problems

Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping

Learning World Models with Identifiable Factorization

Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations

Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks

Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors

Semi-Infinitely Constrained Markov Decision Processes and Efficient Reinforcement Learning

What can online reinforcement learning with function approximation benefit from general coverage conditions?

A Multiplicative Value Function for Safe and Efficient Reinforcement Learning