State of the Art Reinforcement

Reinforcement learning (RL) aims to train agents to make optimal decisions in complex environments by learning from trial and error. Current research focuses on improving credit assignment in challenging scenarios, such as multi-step reasoning tasks for large language models and continuous control in robotics, often employing algorithms like Proximal Policy Optimization (PPO), Soft Actor-Critic (SAC), and variations of Q-learning. These advancements are driving progress in diverse fields, including autonomous driving, robotic manipulation, and resource optimization in areas like power grids and warehouse management, by enabling more efficient and robust decision-making systems.

Papers

August 26, 2022

Symbolic Explanation of Affinity-Based Reinforcement Learning Agents with Markov Models
Charl Maree, Christian W. Omlin
State of the Art Reinforcement Policy Regularization Model Understanding Personalized Incentive Symbolic Language

July 21, 2022

Reinforcement learning for Energies of the future and carbon neutrality: a Challenge Design
Gaëtan Serré, Eva Boguslawski, Benjamin Donnot, Adrien Pavão, Isabelle Guyon, Antoine Marot
Reinforcement Learning Deep Reinforcement Learning Energy Policy Research State of the Art Reinforcement Decarbonization Study Core Challenge Carbon Neutrality

July 8, 2022

Storehouse: a Reinforcement Learning Environment for Optimizing Warehouse Management
Julen Cestero, Marco Quartulli, Alberto Maria Metelli, Marcello Restelli
Reinforcement Learning State of the Art Reinforcement Warehouse Environment

June 23, 2022

Recursive Reinforcement Learning
Ernst Moritz Hahn, Mateo Perez, Sven Schewe, Fabio Somenzi, Ashutosh Trivedi, Dominik Wojtczak
Reinforcement Learning Markov Decision Process Q Learning State of the Art Reinforcement

March 11, 2022

Graph Neural Networks for Relational Inductive Bias in Vision-based Deep Reinforcement Learning of Robot Control
Marco Oliva, Soubarna Banik, Josip Josifovski, Alois Knoll
Reinforcement Learning Graph Neural Network Inductive Bias Robotic Manipulation Robot Control Learned Representation State of the Art Reinforcement Planar Robot

March 2, 2022

Reactive Stepping for Humanoid Robots using Reinforcement Learning: Application to Standing Push Recovery on the Exoskeleton Atalante
Alexis Duburcq, Fabian Schramm, Guilhem Boéris, Nicolas Bredeche, Yann Chevaleyre
Reinforcement Learning Humanoid Robot Bipedal Robot Proprioceptive Sensing State of the Art Reinforcement Push Recovery Stepping Control Passive Exoskeleton

January 22, 2022

Understanding the Effects of Second-Order Approximations in Natural Policy Gradient Reinforcement Learning
Brennan Gebotys, Alexander Wong, David A. Clausi
Mixed Effect Policy Gradient Natural Gradient Second Order Natural Policy Gradient State of the Art Reinforcement

January 21, 2022

Reinforcement Learning Your Way: Agent Characterization through Policy Regularization
Charl Maree, Christian Omlin
Reinforcement Learning High Explainability Model Explanation New Way State of the Art Reinforcement Policy Regularization Post Hoc Explainability Consumption Data Agent Task

January 11, 2022

Benchmarking Deep Reinforcement Learning Algorithms for Vision-based Robotics
Swagat Kumar, Hayden Sampson, Ardhendu Behera
Policy Gradient Proximal Policy Optimization Vision Based Reinforcement Learning Benchmark State of the Art Reinforcement

State of the Art Reinforcement

Papers

Symbolic Explanation of Affinity-Based Reinforcement Learning Agents with Markov Models

Reinforcement learning for Energies of the future and carbon neutrality: a Challenge Design

Storehouse: a Reinforcement Learning Environment for Optimizing Warehouse Management

Recursive Reinforcement Learning

Graph Neural Networks for Relational Inductive Bias in Vision-based Deep Reinforcement Learning of Robot Control

Reactive Stepping for Humanoid Robots using Reinforcement Learning: Application to Standing Push Recovery on the Exoskeleton Atalante

Understanding the Effects of Second-Order Approximations in Natural Policy Gradient Reinforcement Learning

Reinforcement Learning Your Way: Agent Characterization through Policy Regularization

Benchmarking Deep Reinforcement Learning Algorithms for Vision-based Robotics