AAMAS 2024 Tutorial:
Reinforcement Learning for Operations Research: Unlocking New Possibilities


Junjie Sheng¹,	Yun Hua¹,	Wenhao Li²,	Xiangfeng Wang¹

¹East China Normal University, ²The Chinese University of Hong Kong, Shenzhen

Tuesday May 7 14:00 - 18:00 (NZST) @ Grafton, Auckland

QnA: https://bit.ly/rl4or-tutorial

About this tutorial

This half-day tutorial is meticulously crafted to usher participants into the dynamic intersection of reinforcement learning (RL) and operations research (OR). Our aim is to unfold the immense potential of RL in addressing a broad spectrum of OR challenges, especially for cloud resource scheduling and multi-agent pathfinding. This enriching journey will navigate through key areas including the scope of OR, the synergy between RL and OR, diverse industry case studies (including Huawei Cloud and Geekplus Inc.), and pioneering future directions in both realms. Participants will be immersed in a hands-on learning environment, engaging in interactive sessions and comprehensive case studies. This experience is designed to equip attendees with the skills to apply RL strategies to real-world OR problems effectively. The tutorial caters specifically to RL professionals and enthusiasts eager to expand their horizons into the vast domain of OR. By the conclusion of this tutorial, attendees will not only develop a deep appreciation for the diversity of OR problems but also acquire the capability to devise and implement innovative RL solutions. We encourage an environment of active engagement, inviting attendees to partake in discussions and share their experiences and perspectives at the confluence of RL and OR.

Schedule

Our tutorial will be held on May 7 (all the times are based on NZST = New Zealand local time). Slides may be subject to updates.

Time	Section	Presenter
14:00—14:55	Section 1: Introduction, Definition & Preliminaries [Slides]	Xiangfeng
14:55—15:55	Section 2: Reinforcement Learning for VM Scheduling [Slides]	Junjie
15:55—16:00	Q & A Session I
16:00—16:30	Coffee break
16:30—17:30	Section 3: Reinforcement Learning for Multi-Agent Pathfinding [Slides]	Wenhao
17:30—17:40	Q & A Session II

Reading List

Section 1: Introduction

Mathematical discoveries from program search with large language models. (Romera-Paredes et al., 2023)
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping. (Lehnert et al., 2024)
Large Language Models as Evolutionary Optimizers. (Liu et al., 2023)
Artificial Intelligence for Operations Research: Revolutionizing the Operations Research Process. (Fan et al., 2024)
Can Language Agents Approach the Performance of RL? An Empirical Study On OpenAI Gym. (Sheng et al., 2023)
Foundation models for decision making: Problems, methods, and opportunities. (Yang et al., 2023)
Video as the New Language for Real-World Decision Making. (Du et al., 2024)

Section 2: VM Scheduling

Learning to schedule multi-NUMA virtual machines via reinforcement learning (Sheng et al., 2022)
Hindsight Learning for MDPs with Exogenous Inputs (Sinclair et al., 2022)
Mathematical discoveries from program search with large language models (Romera-Paredes et al., 2023)
Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning (Sheng et al., 2023)

Section 3: Multi-Agent Pathfinding

Multi-agent path planning in unknown environment with reinforcement learning and neural network (Cruz et al. 2014)
Multi-agent navigation based on deep reinforcement learning and traditional pathfinding algorithm (Qiu et al. 2020)
PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning (PRIMAL (Sartoretti el al. 2019))
Mobile Robot Path Planning in Dynamic Environments Through Globally Guided Reinforcement Learning (G2RL (Wang et al. 2020))
MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments (MAPPER (Liu et al. 2020))
PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Lifelong (PRIMAL2 (Damani et al. 2021))
Multi-robot path planning based on a deep reinforcement learning DQN algorithm (Yang, et al. 2020)
Distributed Heuristic Multi-Agent Path Finding with Communication (DHC (Ma et al. 2021))
Q-Mixing Network for Multi-Agent Pathfinding in Partially Observable Grid Environments (Davydov et al. 2021)
Learning Selective Communication for Multi-Agent Path Finding (DCC (Ma et al. 2021))
Multi-Agent Path Finding with Prioritized Communication Learning (PICO (Li et al. 2022))
AB-Mapper: Attention and BicNet based Multi-agent Path Planning for Dynamic Environment (AB-MAPPER (Guan et al. 2021))
Hybrid Policy Learning for Multi-Agent Pathfinding (Skrynnik et al. 2021)
Flatland-RL : Multi-Agent Reinforcement Learning on Trains (Flatland-RL (Mohanty et al. 2020))
Multi-Agent Pathfinding for Deadlock Avoidance on Rotational Movements (MAPF-ROT (Chan et al. 2022))
Learning to Cooperate: Application of Deep Reinforcement Learning for Online AGV Path Finding (Zhang et al. 2020)
Anti-conflict AGV path planning in automated container terminals based on multi-agent reinforcement learning (Hu et al. 2023)
SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding (SCRIMP (Wang et al. 2023))
Curriculum Learning Based Multi-Agent Path Finding for Complex Environments (CPL (Zhao et al. 2023))
Decentralized Monte Carlo Tree Search for Partially Observable Multi-Agent Pathfinding (MATS-LP (Skrynnik et al. 2023))
Multiagent Path Finding Using Deep Reinforcement Learning Coupled With Hot Supervision Contrastive Loss (Chen et al. 2023b)
Time-Constrained Multi-Agent Path Finding in Non-Lattice Graphs with Deep Reinforcement Learning (Knippenberg et al. 2021)
SACHA: Soft Actor-Critic With Heuristic-Based Attention for Partially Observable Multi-Agent Path Finding (SACHA (Lin et al. 2023))
Transformer-Based Imitative Reinforcement Learning for Multirobot Path Planning (Chen et al. 2023a)
Towards Deployment-Efficient and Collision-Free Multi-Agent Path Finding (Student Abstract) (Chen et al. 2023c)
HELSA: Hierarchical Reinforcement Learning with Spatiotemporal Abstraction for Large-Scale Multi-Agent Path Finding (HELSA (Song et al. 2023))
Learn to Follow: Decentralized Lifelong Multi-Agent Pathfinding via Planning and Learning (Follower (Skrynnik et al. 2023))
Attention-based Priority Learning for Limited Time Multi-Agent Path Finding (S2AN (Yang et al. 2024))
ALPHA: Attention-based Long-horizon Pathfinding in Highly-structured Areas (ALPHA (He et al. 2023))
Distributed multi-robot collision avoidance via deep reinforcement learning for navigation in complex scenarios (Fan et al. 2020)
Optimizing Field-of-View for Multi-Agent Path Finding via Reinforcement Learning: A Performance and Communication Overhead Study (Cheng et al. 2023)
Confidence-Based Curriculum Learning for Multi-Agent Path Finding (CACTUS (Phan et al. 2024))
Optimizing Crowd-Aware Multi-Agent Path Finding through Local Broadcasting with Graph Neural Networks (CRAMP (Pham et al. 2024))
When to Switch: Planning and Learning for Partially Observable Multi-Agent Pathfinding. (Skrynnik et al. 2023)

BibTeX

@article{ rl4or-tutorial,
  author    = { Sheng, Junjie and Hua, Yun and Li, Wenhao and Wang, Xiangfeng },
  title     = { AAMAS 2024 Tutorial: Reinforcement Learning for Operations Research: Unlocking New Possibilities },
  journal   = { AAMAS 2024 },
  year      = { 2024 },
}