Optimal Strategy

Optimal strategy research focuses on identifying the best course of action within various contexts, from game theory and machine learning to resource allocation and decision-making under uncertainty. Current research emphasizes developing and analyzing algorithms, including reinforcement learning, generative adversarial networks, and physics-informed neural networks, to find optimal strategies in complex environments with incomplete information or adversarial interactions. These advancements have implications for diverse fields, improving efficiency in areas like online advertising, resource management, and even the design of AI agents for games and autonomous systems. The ultimate goal is to create robust and adaptable strategies that achieve desired outcomes even in unpredictable or competitive settings.

Papers

March 9, 2023

Time-Dependent Blackwell Approachability and Application to Absorbing Games
Joon Kwon, Yijun Wan, Bruno Ziliotto
Stochastic Game Vector Valued Optimal Strategy Dot Product Mutual Influence Approachability Problem

March 4, 2023

Adaptive Predictive Portfolio Management Agent
Anton Kolonin, Alexey Glushchenko, Arseniy Fokin, Marcello Mari, Mario Casiraghi, Mukul Vishwas
Optimal Strategy Portfolio Optimization

February 2, 2023

Follower Agnostic Methods for Stackelberg Games
Chinmay Maheshwari, James Cheng, S. Shankar Sasty, Lillian Ratliff, Eric Mazumdar
Strategy Logic Optimal Strategy Stackelberg Game Agnostic Approach Stackelberg Equilibrium

January 26, 2023

Cluster Forming of Multiagent Systems in Rolling Horizon Games with Non-uniform Horizons
Yurid Nugraha, Ahmet Cetinkaya, Tomohisa Hayakawa, Hideaki Ishii, Quanyan Zhu
Consensus Group Decision Cluster Structure Multiagent System Optimal Strategy Prediction Horizon Jamming Attack

January 9, 2023

A Rolling Horizon Game Considering Network Effect in Cluster Forming for Dynamic Resilient Multiagent Systems
Yurid Nugraha, Ahmet Cetinkaya, Tomohisa Hayakawa, Hideaki Ishii, Quanyan Zhu
Cluster Structure Optimal Strategy Network Resilience Bipartite Consensus Network Effect

November 15, 2022

Reinforcement Learning Methods for Wordle: A POMDP/Adaptive Control Approach
Siddhant Bhambri, Amrita Bhattacharjee, Dimitri Bertsekas
Reinforcement Learning Sequential Decision Making Problem Observable Markov Decision Process Adaptive Control Partially Observable Markov Decision Process Optimal Strategy Wordle Game

August 11, 2022

Multi-Agent Reinforcement Learning with Graph Convolutional Neural Networks for optimal Bidding Strategies of Generation Units in Electricity Markets
Pegah Rokhforoz, Olga Fink
Deep Reinforcement Learning Multi Agent Reinforcement Learning Graph Convolutional Neural Network Optimal Strategy Electricity Market Optimal Bidding Strategy Bidding Strategy

June 13, 2022

Reinforcement Learning-based Placement of Charging Stations in Urban Road Networks
Leonie von Wahl, Nicolas Tempelmeier, Ashutosh Sao, Elena Demidova
Deep Reinforcement Learning Positive Reinforcement Mobility Management Optimal Strategy Optimal Service Station Design Optimal Placement Electric Vehicle Charging Station Stable Placement Urban Road Network

May 29, 2022

No-regret Learning in Repeated First-Price Auctions with Budget Constraints
Rui Ai, Chang Wang, Chenchen Li, Jinshan Zhang, Wenhan Huang, Xiaotie Deng
Optimal Strategy Budget Constraint Price Auction Regret Learning Bidding Strategy

April 20, 2022

Reinforcement Learning with Intrinsic Affinity for Personalized Prosperity Management
Charl Maree, Christian W. Omlin
Reinforcement Learning Optimal Strategy Balancing Efficiency Policy Alignment Personalized Incentive

April 4, 2022

Reinforcement Learning Agents in Colonel Blotto
Joseph Christian G. Noel
Reinforcement Learning Reinforcement Learning Agent Agent Based Model Artificial Agent Optimal Strategy

March 29, 2022

February 12, 2022

Learning Revenue Maximization using Posted Prices for Stochastic Strategic Patient Buyers
Eitan-Hai Mashiah, Idan Attias, Yishay Mansour
Curious Price Optimal Strategy Stackelberg Equilibrium Revenue Maximization

February 11, 2022

A PDE-Based Analysis of the Symmetric Two-Armed Bernoulli Bandit
Vladimir A. Kobzar, Robert V. Kohn
General Analysis Optimal Strategy Minimax Regret Two Armed

February 1, 2022

Finding the optimal human strategy for Wordle using maximum correct letter probabilities and reinforcement learning
Benton J. Anderson, Jesse G. Meyer
Reinforcement Learning Optimal Strategy Wordle Game

January 31, 2022

Score vs. Winrate in Score-Based Games: which Reward for Reinforcement Learning?
Luca Pasqualini, Gianluca Amato, Marco Fantozzi, Rosa Gini, Alessandro Marchetti, Carlo Metta, Francesco Morandin, Maurizio Parton
Reinforcement Learning Reward Report Performance Score Zero Sum Game Score Based Optimal Strategy Deterministic Game

January 19, 2022

PDE-Based Optimal Strategy for Unconstrained Online Learning
Zhiyu Zhang, Ashok Cutkosky, Ioannis Paschalidis
Novel Algorithm Optimal Strategy Online Linear Potential Function

November 29, 2021

Final Adaptation Reinforcement Learning for N-Player Games
Wolfgang Konen, Samineh Bagheri
Reinforcement Learning Q Learning Optimal Strategy Board Game Player Game

November 15, 2021

Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation
David Acuna, Jonah Philion, Sanja Fidler
Autonomous Driving Domain Adaptation Simulation Study Bird'S Eye View Vehicle Perception Optimal Strategy Driving Simulator Perception Network

Optimal Strategy

Papers

Time-Dependent Blackwell Approachability and Application to Absorbing Games

Adaptive Predictive Portfolio Management Agent

Follower Agnostic Methods for Stackelberg Games

Cluster Forming of Multiagent Systems in Rolling Horizon Games with Non-uniform Horizons

A Rolling Horizon Game Considering Network Effect in Cluster Forming for Dynamic Resilient Multiagent Systems

Reinforcement Learning Methods for Wordle: A POMDP/Adaptive Control Approach

Multi-Agent Reinforcement Learning with Graph Convolutional Neural Networks for optimal Bidding Strategies of Generation Units in Electricity Markets

Reinforcement Learning-based Placement of Charging Stations in Urban Road Networks

No-regret Learning in Repeated First-Price Auctions with Budget Constraints

Reinforcement Learning with Intrinsic Affinity for Personalized Prosperity Management

Reinforcement Learning Agents in Colonel Blotto

Proximal-like algorithms for equilibrium seeking in mixed-integer Nash equilibrium problems

Learning to act: a Reinforcement Learning approach to recommend the best next activities

Learning Revenue Maximization using Posted Prices for Stochastic Strategic Patient Buyers

A PDE-Based Analysis of the Symmetric Two-Armed Bernoulli Bandit

Finding the optimal human strategy for Wordle using maximum correct letter probabilities and reinforcement learning

Score vs. Winrate in Score-Based Games: which Reward for Reinforcement Learning?

PDE-Based Optimal Strategy for Unconstrained Online Learning

Final Adaptation Reinforcement Learning for N-Player Games

Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation