Diverse Strategy

Diverse strategy research explores methods for developing and utilizing multiple, distinct approaches to problem-solving, particularly within complex systems like reinforcement learning and multi-attribute decision-making. Current research focuses on developing algorithms and models that efficiently discover and optimize diverse strategies, often incorporating techniques like population-based training, iterative learning, and novel diversity measures based on state-space distances or information-theoretic objectives. This work has significant implications for improving the robustness, adaptability, and human-interpretability of AI systems across various applications, from robotics and game playing to medical image analysis and educational interventions.

Papers

June 20, 2024

Mask the Unknown: Assessing Different Strategies to Handle Weak Annotations in the MICCAI2023 Mediastinal Lymph Node Quantification Challenge
Stefan M. Fischer, Johannes Kiechle, Daniel M. Lang, Jan C. Peeken, Julia A. Schnabel
Mask Frozen DETR Lymph Node Weak Annotation Diverse Strategy Mediastinal Lymph Node

January 22, 2024

On the impact of robot personalization on human-robot interaction: A review
Jinyu Yang, Camille Vindolet, Julio Rogelio Guadarrama Olvera, Gordon Cheng
Global Impact Narrative Review Mixed Effect Human Robot Interaction Personalized Model Diverse Strategy Personalized Robot

October 23, 2023

Iteratively Learn Diverse Strategies with State Distance Information
Wei Fu, Weihua Du, Jingwei Li, Sunli Chen, Jingzhao Zhang, Yi Wu
Reinforcement Learning Multi Agent Diversity Metric Distance Information Diversity Reinforcement Learning Diverse Strategy Agnostic Reinforcement Learning

July 5, 2023

Analyzing Different Expert-Opined Strategies to Enhance the Effect on the Goal of a Multi-Attribute Decision-Making System Using a Concept of Effort Propagation and Application in Enhancement of High School Students' Performance
Suvojit Dhara, Adrijit Goswami
Feature Enhancement High Impact Concept Multi Criterion Decision Diverse Strategy Effort Propagation

June 1, 2023

Effect of Monetary Reward on Users' Individual Strategies Using Co-Evolutionary Learning
Shintaro Ueki, Fujio Toriumi, Toshiharu Sugawara
Mixed Effect Game Theoretic User Base User Generated Content Diverse Strategy Monetary Reward

May 6, 2023

SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition
Shuzheng Si, Zefan Cai, Shuang Zeng, Guoqiang Feng, Jiaxing Lin, Baobao Chang
Entity Recognition Entity Representation Selective Annotation Text Normalization Unreliable Source Ambiguous Entity Diverse Strategy

February 25, 2023

Hierarchical Needs-driven Agent Learning Systems: From Deep Reinforcement Learning To Diverse Strategies
Qin Yang
Deep Reinforcement Learning Multi Agent System AI Agent Single Robot Diverse Strategy

January 25, 2023

DIFFER: Decomposing Individual Reward for Fair Experience Replay in Multi-Agent Reinforcement Learning
Xunhan Hu, Jian Zhao, Wengang Zhou, Ruili Feng, Houqiang Li
Multi Agent Reinforcement Learning Reward Function Reward Model Cooperative Multi Agent Reinforcement Learning Experience Replay Diverse Strategy Social Reward

November 4, 2022

Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI
Emily Halina, Matthew Guzdial
AI Agent Game AI Diversity Reinforcement Learning Diverse Strategy Antagonistic AI

July 12, 2022

DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization
Wentse Chen, Shiyu Huang, Yuan Chiang, Tim Pearce, Wei-Wei Tu, Ting Chen, Jun Zhu
Policy Reinforcement Learning Policy Iteration Reinforcement Learning Task Diversity Reinforcement Learning Diverse Strategy Multiple Strategy

April 30, 2022

Using Wordle for Learning to Design and Compare Strategies
Chao-Lin Liu
LeArning Abstract Product Design Wordle Game Diverse Strategy

Diverse Strategy

Papers

Mask the Unknown: Assessing Different Strategies to Handle Weak Annotations in the MICCAI2023 Mediastinal Lymph Node Quantification Challenge

On the impact of robot personalization on human-robot interaction: A review

Iteratively Learn Diverse Strategies with State Distance Information

Analyzing Different Expert-Opined Strategies to Enhance the Effect on the Goal of a Multi-Attribute Decision-Making System Using a Concept of Effort Propagation and Application in Enhancement of High School Students' Performance

Effect of Monetary Reward on Users' Individual Strategies Using Co-Evolutionary Learning

SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition

Hierarchical Needs-driven Agent Learning Systems: From Deep Reinforcement Learning To Diverse Strategies

DIFFER: Decomposing Individual Reward for Fair Experience Replay in Multi-Agent Reinforcement Learning

Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI

DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization

Using Wordle for Learning to Design and Compare Strategies