Robust Strategy

Robust strategy research focuses on designing systems and algorithms that maintain reliable performance despite uncertainties, adversarial attacks, or unexpected disturbances. Current efforts concentrate on developing learning-based controllers, often employing neural networks or reinforcement learning, to achieve robustness in diverse applications like robotics, recommendation systems, and financial modeling. These advancements are crucial for deploying AI systems in real-world scenarios demanding safety and reliability, improving the trustworthiness and effectiveness of AI across various domains. The development of robust strategies is driving progress in both theoretical understanding of system vulnerabilities and practical improvements in the resilience of AI-driven technologies.

Papers

November 14, 2024

Nash equilibrium seeking for a class of quadratic-bilinear Wasserstein distributionally robust games
Georgios Pantazis, Reza Rahimi Bahbadorani, Sergio Grammatico
Nash Equilibrium True Class Efficient Equilibrium Robust Strategy Approximate Equilibrium

November 2, 2024

Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity
Emiliyan Gospodinov, Vaisakh Shaj, Philipp Becker, Stefan Geyer, Gerhard Neumann
World Model Non Stationary Environment Non Stationarity POMDP Policy Behaviour Learning Robust Strategy Latent Imagination

October 30, 2024

Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning
Yiqin Lv, Qi Wang, Dong Liang, Zheng Xie
Meta Learning Feature Enhancement Theoretical Analysis Distributional Robustness Risk Minimization Robust Adaptation Risk Measure Robust Strategy

September 23, 2024

Robust Continuous Motion Strategy Against Muscle Rupture using Online Learning of Redundant Intersensory Networks for Musculoskeletal Humanoids
Kento Kawaharazuka, Manabu Nishiura, Yasunori Toshimitsu, Yusuke Omura, Yuya Koga, Yuki Asano, Koji Kawasaki, Masayuki Inaba
Online Learning Musculoskeletal Humanoid Multi Sensory Robust Strategy Muscle Synergy

September 7, 2024

Learning to Open and Traverse Doors with a Legged Manipulator
Mike Zhang, Yuntao Ma, Takahiro Miki, Marco Hutter
LeArning Abstract Robotics Domain Legged Robot Learning Based Robust Strategy Legged Manipulator

July 2, 2024

Sequential Manipulation Against Rank Aggregation: Theory and Algorithm
Ke Ma, Qianqian Xu, Jinshan Zeng, Wei Liu, Xiaochun Cao, Yingfei Sun, Qingming Huang
Practical Algorithm Theoretical Understanding Game Theoretic Pairwise Comparison Sequential Manipulation Rank Aggregation Robust Strategy

April 14, 2024

Distilling Reasoning Ability from Large Language Models with Adaptive Thinking
Xiaoshu Chen, Sihang Zhou, Ke Liang, Xinwang Liu
Complex Reasoning Reasoning Task Reasoning Capability LLM Reasoning Reasoning Process Robust Strategy

April 7, 2024

Quantifying AI Vulnerabilities: A Synthesis of Complexity, Dynamical Systems, and Game Theory
B Kereopa-Yorke
Dynamical System Complexity Matter Critical Synthesis Game Theory Robust Evaluation Artificial Intelligence Security Robust Strategy AI Vulnerability

March 6, 2024

Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation
Marcel Torne, Anthony Simeonov, Zechu Li, April Chan, Tao Chen, Abhishek Gupta, Pulkit Agrawal
Reinforcement Learning Imitation Learning Real World Simulation Study Robust Policy Sim to Real Robust Manipulation Robust Strategy

October 25, 2023

Pretty Good Strategies and Where to Find Them
Wojciech Jamroga, Damian Kurpiewski
General Strategy Simple Strategy Robust Strategy Goal Reachability

October 15, 2023

Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization
Simin Li, Ruixiao Xu, Jingqiao Xiu, Yuwei Zheng, Pu Feng, Yaodong Yang, Xianglong Liu
Multi Agent Reinforcement Learning Robust Strategy Worst Case Robustness Mutual Information Regularization Action Prior

August 23, 2023

Robustness Analysis of Continuous-Depth Models with Lagrangian Techniques
Sophie A. Neubauer, Radu Grosu
Depth Distribution Statistical Guarantee Robustness Analysis Lagrangian Method Robust Strategy

August 13, 2023

CDR: Conservative Doubly Robust Learning for Debiased Recommendation
ZiJie Song, JiaWei Chen, Sheng Zhou, QiHao Shi, Yan Feng, Chun Chen, Can Wang
Recommendation System Robust Learning Knowledge Enhanced Conditional Imputation Debiased Recommendation Robust Strategy Doubly Robust

May 27, 2023

Choosing the Right Weights: Balancing Value, Strategy, and Noise in Recommender Systems
Smitha Milli, Emma Pierson, Nikhil Garg
Recommender System Industrial Disturbing Noise User Behavior Strategy Logic Balancing Weight Net Present Value Robust Strategy Linear Weighting Many Recommender System

March 27, 2023

Robust Risk-Aware Option Hedging
David Wu, Sebastian Jaimungal
Hedging Strategy Robust Strategy Risk Aware Reinforcement Learning Dynamic Hedging Path Dependent Option

February 17, 2022

Robust Reinforcement Learning via Genetic Curriculum
Yeeho Song, Jeff Schneider
Deep Reinforcement Learning Native Robustness Robust Reinforcement Learning Adversarial Agent Robust Strategy Evolutionary Curriculum