Reinforcement Learning Paradigm

Reinforcement learning (RL) is a machine learning paradigm focused on training agents to make optimal decisions in dynamic environments by maximizing cumulative rewards. Current research emphasizes improving RL's efficiency and robustness, exploring architectures like concurrent teacher-student models and algorithms that decouple exploration and exploitation to avoid suboptimal solutions. These advancements are driving progress in robotics, particularly legged locomotion and manipulation, as well as addressing challenges in interpretability and safe exploration within RL frameworks. The broader impact spans diverse fields, from autonomous systems to optimizing complex decision-making processes.

Papers

October 9, 2024

ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model
Gaoge Han, Mingjiang Liang, Jinglei Tang, Yongkang Cheng, Wei Liu, Shaoli Huang
Reinforcement Learning Motion Generation Motion Diffusion Model Future Motion Plausible Human Motion Reinforcement Learning Paradigm

May 17, 2024

CTS: Concurrent Teacher-Student Reinforcement Learning for Legged Locomotion
Hongxi Wang, Haoxiang Luo, Wei Zhang, Hua Chen
Reinforcement Learning Representation Learning Legged Locomotion Robust Locomotion Reinforcement Learning Paradigm

April 16, 2024

Towards a Research Community in Interpretable Reinforcement Learning: the InterpPol Workshop
Hector Kohler, Quentin Delfosse, Paul Festor, Philippe Preux
Reinforcement Learning Explainable Reinforcement Learning Research Community Interpretable Policy Reinforcement Learning Paradigm

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

October 9, 2023

Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments
Xiong-Hui Chen, Junyin Ye, Hang Zhao, Yi-Chen Li, Haoran Shi, Yu-Yan Xu, Zhihao Ye, Si-Hang Yang, Anqi Huang, Kai Xu, Zongzhang Zhang, Yang Yu
Imitation Learning Imitation Policy Reinforcement Learning Paradigm Imitation Learned Policy Imitation Ability Imitator Learning

October 3, 2023

What do we learn from a large-scale study of pre-trained visual representations in sim and real environments?
Sneha Silwal, Karmesh Yadav, Tingfan Wu, Jay Vakil, Arjun Majumdar, Sergio Arnaud, Claire Chen, Vincent-Pierre Berges, Dhruv Batra, Aravind Rajeswaran, Mrinal Kalakrishnan, Franziska Meier, Oleksandr Maksymets
Reinforcement Learning Pre Trained Representation Real World Environment Indoor Navigation Reinforcement Learning Paradigm

August 18, 2023

A Robust Policy Bootstrapping Algorithm for Multi-objective Reinforcement Learning in Non-stationary Environments
Sherif Abdelfattah, Kathryn Kasmarik, Jiankun Hu
Multi Objective Reinforcement Learning Robust Policy Non Stationary Environment Reinforcement Learning Paradigm Multi Objective Markov Decision Process

January 13, 2023

A Constrained-Optimization Approach to the Execution of Prioritized Stacks of Learned Multi-Robot Tasks
Gennaro Notomista
Constrained Optimization Robotic Task Multi Robot Task Multi Robot Coordination Software Stack Reinforcement Learning Paradigm

October 1, 2022

Deep Intrinsically Motivated Exploration in Continuous Control
Baturay Saglam, Suleyman S. Kozat
Continuous Control Intrinsic Motivation Pure Exploration Reinforcement Learning Paradigm Intrinsic Exploration

June 28, 2022

Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL
Ruiquan Huang, Jing Yang, Yingbin Liang
Sample Complexity Near Optimal Policy Safe Exploration Reward Free Reinforcement Learning Reward Free Exploration Reinforcement Learning Paradigm

April 11, 2022

Implementing Online Reinforcement Learning with Temporal Neural Networks
James E. Smith
Online Reinforcement Learning Efficient Reinforcement Learning Temporal Neural Network Reinforcement Learning Paradigm

February 3, 2022

Reward is not enough: can we liberate AI from the reinforcement learning paradigm?
Vacslav Glukhov
Artificial Intelligence Intelligent Agent Reward Report Reward Maximization Intelligent Behaviour Reinforcement Learning Paradigm

Reinforcement Learning Paradigm

Papers

ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model

CTS: Concurrent Teacher-Student Reinforcement Learning for Legged Locomotion

Towards a Research Community in Interpretable Reinforcement Learning: the InterpPol Workshop

Efficient Reinforcement Learning via Decoupling Exploration and Utilization

Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments

What do we learn from a large-scale study of pre-trained visual representations in sim and real environments?

A Robust Policy Bootstrapping Algorithm for Multi-objective Reinforcement Learning in Non-stationary Environments

A Constrained-Optimization Approach to the Execution of Prioritized Stacks of Learned Multi-Robot Tasks

Deep Intrinsically Motivated Exploration in Continuous Control

Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL

Implementing Online Reinforcement Learning with Temporal Neural Networks

Reward is not enough: can we liberate AI from the reinforcement learning paradigm?