Reinforcement Learning

Reinforcement learning (RL) focuses on training agents to make optimal decisions in an environment by learning through trial and error, aiming to maximize cumulative rewards. Current research emphasizes improving RL's efficiency and robustness, particularly in areas like human-in-the-loop training (e.g., using human feedback to refine models), handling uncertainty and sparse rewards, and scaling to complex tasks (e.g., robotics, autonomous driving). Prominent approaches involve various policy gradient methods, Monte Carlo Tree Search, and the integration of large language models for improved decision-making and task decomposition. These advancements are driving progress in diverse fields, including robotics, game playing, and the development of more human-aligned AI systems.

Papers

September 25, 2024

On-orbit Servicing for Spacecraft Collision Avoidance With Autonomous Decision Making
Susmitha Patnala, Adam Abdin
Reinforcement Learning Collision Avoidance Autonomous Decision Making Orbit Servicing
Reinforcement Learning for Finite Space Mean-Field Type Games
Kai Shao, Jiacheng Shen, Chijie An, Mathieu Laurière
Reinforcement Learning Q Learning Mean Field Game
A random measure approach to reinforcement learning in continuous time
Christian Bender, Nguyen Tran Thuan
Reinforcement Learning Continuous Time Diffusion SDE
Dynamic Obstacle Avoidance through Uncertainty-Based Adaptive Planning with Diffusion
Vineet Punyamoorty, Pascal Jutras-Dubé, Ruqi Zhang, Vaneet Aggarwal, Damon Conover, Aniket Bera
Reinforcement Learning Diffusion Explainer Collision Avoidance Obstacle Avoidance Uncertainty Aware Long Horizon Planning Robust Obstacle Avoidance Generative Planning
Behavior evolution-inspired approach to walking gait reinforcement training for quadruped robots
Yu Wang, Wenchuan Jia, Yi Sun, Dong He
Reinforcement Learning Non Humanoid Robot Quadrupedal Robot BEHAVIOR Explanation Evolutionary Approach Gait Generation
OffRIPP: Offline RL-based Informative Path Planning
Srikar Babu Gadipudi, Srujan Deolasee, Siva Kailas, Wenhao Luo, Katia Sycara, Woojun Kim
Reinforcement Learning Robotics Domain Action Free Offline Informative Path Planning Real World Experiment Batch Reinforcement Learning
Symbolic State Partition for Reinforcement Learning
Mohsen Ghaffari, Mahsa Varshosaz, Einar Broch Johnsen, Andrzej Wąsowski
Reinforcement Learning State Space Tabular Reinforcement Learning Finite State
Offline and Distributional Reinforcement Learning for Radio Resource Management
Eslam Eldeeb, Hirley Alves
Reinforcement Learning Distributional Reinforcement Learning Action Free Offline Stochastic Environment Radio Resource Management Future Network
Optimized Monte Carlo Tree Search for Enhanced Decision Making in the FrozenLake Environment
Esteban Aldana Guerra
Reinforcement Learning Q Learning Monte Carlo Tree Search Decision Problem Decision Making Algorithm Coniferous Forest

September 24, 2024

From Goal-Conditioned to Language-Conditioned Agents via Vision-Language Models
Theo Cachet, Christopher R. Dance, Olivier Sigaud
Reinforcement Learning Vision Language Model Multi Task Human Language Simple Function Bridging Text Language Conditioned Single Agent Reinforcement Learning
Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach
Dohyeong Kim, Hyeokjin Kwon, Junseok Kim, Gunmin Lee, Songhwai Oh
Reinforcement Learning Reward Function Multi Objective Reinforcement Learning Reward Shaping
Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm
Yooseok Lim, Inbeom Park, Sujee Lee
Reinforcement Learning Offline Reinforcement Learning Development Activity External Validation
Walking with Terrain Reconstruction: Learning to Traverse Risky Sparse Footholds
Ruiqi Yu, Qianshi Wang, Yizhen Wang, Zhicheng Wang, Jun Wu, Qiuguo Zhu
Reinforcement Learning Legged Robot Robust Locomotion Rough Terrain Safe Foothold Terrain Estimation
SurgIRL: Towards Life-Long Learning for Surgical Automation by Incremental Reinforcement Learning
Yun-Jie Ho, Zih-Yun Chiu, Yuheng Zhi, Michael C. Yip
Reinforcement Learning Lifelong Learning Surgical Automation Surgical Task

September 23, 2024

Physics Enhanced Residual Policy Learning (PERPL) for safety cruising in mixed traffic platooning under actuator and communication delay
Keke Long, Haotian Shi, Yang Zhou, Xiaopeng Li
Reinforcement Learning Human SAFETY Mixed Traffic Physic Aware New Unimorph Actuator Vehicle Control Communication Delay Residual Physic
Learning Diverse Robot Striking Motions with Diffusion Models and Kinematically Constrained Gradient Guidance
Kin Man Lee, Sean Ye, Qingyu Xiao, Zixuan Wu, Zulfiqar Zaidi, David B. D'Ambrosio, Pannag R. Sanketi, Matthew Gombolay
Reinforcement Learning Diffusion Model Robot Learning Robot Motion Robot Safety Diverse Behavior Gradient Guidance
CANDERE-COACH: Reinforcement Learning from Noisy Feedback
Yuxuan Li, Srijita Das, Matthew E. Taylor
Reinforcement Learning Imitation Learning Inverse Reinforcement Learning Noisy Feedback Human COACH AI Coach
Intelligent Routing Algorithm over SDN: Reusable Reinforcement Learning Approach
Wang Wumian, Sajal Saha, Anwar Haque, Greg Sidebottom
Reinforcement Learning Dynamic Routing Routing Problem Software Defined Intelligent Routing
SPformer: A Transformer Based DRL Decision Making Method for Connected Automated Vehicles
Ye Han, Lijun Zhang, Dejian Meng, Xingyu Hu, Yixia Lu
Reinforcement Learning Practical Method Multi Agent Deep Reinforcement Learning Connected Autonomous Vehicle Mixed Autonomy Traffic Multi Robot Decision Making
Deep Reinforcement Learning-based Obstacle Avoidance for Robot Movement in Warehouse Environments
Keqin Li, Jiajing Chen, Denzhi Yu, Tao Dajun, Xinyu Qiu, Lian Jieting, Sun Baiwei, Zhang Shengyuan, Zhenyu Wan, Ran Ji, Bo Hong, Fanghao Ni
Reinforcement Learning Obstacle Avoidance Robot Motion Deep Reinforcement Warehouse Environment Based Obstacle Avoidance Warehouse Robot

Reinforcement Learning

Papers

On-orbit Servicing for Spacecraft Collision Avoidance With Autonomous Decision Making

Reinforcement Learning for Finite Space Mean-Field Type Games

A random measure approach to reinforcement learning in continuous time

Dynamic Obstacle Avoidance through Uncertainty-Based Adaptive Planning with Diffusion

Behavior evolution-inspired approach to walking gait reinforcement training for quadruped robots

OffRIPP: Offline RL-based Informative Path Planning

Symbolic State Partition for Reinforcement Learning

Offline and Distributional Reinforcement Learning for Radio Resource Management

Optimized Monte Carlo Tree Search for Enhanced Decision Making in the FrozenLake Environment

From Goal-Conditioned to Language-Conditioned Agents via Vision-Language Models

Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach

Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm

Walking with Terrain Reconstruction: Learning to Traverse Risky Sparse Footholds

SurgIRL: Towards Life-Long Learning for Surgical Automation by Incremental Reinforcement Learning

Physics Enhanced Residual Policy Learning (PERPL) for safety cruising in mixed traffic platooning under actuator and communication delay

Learning Diverse Robot Striking Motions with Diffusion Models and Kinematically Constrained Gradient Guidance

CANDERE-COACH: Reinforcement Learning from Noisy Feedback

Intelligent Routing Algorithm over SDN: Reusable Reinforcement Learning Approach

SPformer: A Transformer Based DRL Decision Making Method for Connected Automated Vehicles

Deep Reinforcement Learning-based Obstacle Avoidance for Robot Movement in Warehouse Environments