Sequential information design: Learning to persuade in the dark
We study a repeated information design problem faced by an informed sender who tries to
influence the behavior of a self-interested receiver. We consider settings where the receiver …
influence the behavior of a self-interested receiver. We consider settings where the receiver …
Safe learning in tree-form sequential decision making: Handling hard and soft constraints
We study decision making problems in which an agent sequentially interacts with a
stochastic environment defined by means of a tree structure. The agent repeatedly faces the …
stochastic environment defined by means of a tree structure. The agent repeatedly faces the …
Safe opponent-exploitation subgame refinement
In zero-sum games, an NE strategy tends to be overly conservative confronted with
opponents of limited rationality, because it does not actively exploit their weaknesses. From …
opponents of limited rationality, because it does not actively exploit their weaknesses. From …
Kdb-D2CFR: Solving Multiplayer imperfect-information games with knowledge distillation-based DeepCFR
H Li, Z Guo, Y Liu, X Wang, S Qi, J Zhang… - Knowledge-Based …, 2023 - Elsevier
Counterfactual regret minimization (CFR) is a popular method for finding approximate Nash
equilibrium in imperfect-information games (IIG). However, CFR based methods for the IIG …
equilibrium in imperfect-information games (IIG). However, CFR based methods for the IIG …
Online learning in sequential Bayesian persuasion: Handling unknown priors
We study a repeated information design problem faced by an informed sender who tries to
influence the behavior of a self-interested receiver, through the provision of payoff-relevant …
influence the behavior of a self-interested receiver, through the provision of payoff-relevant …
Modeling rationality: Toward better performance against unknown agents in sequential games
Opponent modeling is necessary for autonomous agents to capture the intents of others
during strategic interactions. Most previous works assume that they can access enough …
during strategic interactions. Most previous works assume that they can access enough …
A General Framework for Safe Decision Making: A Convex Duality Approach
We study the problem of online interaction in general decision making problems, where the
objective is not only to find optimal strategies, but also to satisfy some safety guarantees …
objective is not only to find optimal strategies, but also to satisfy some safety guarantees …
A framework for safe decision making: A convex duality approach
We study the problem of online interaction in general decision making problems, where the
objective is not only to find optimal strategies, but also to satisfy certain safety guarantees …
objective is not only to find optimal strategies, but also to satisfy certain safety guarantees …
Safe and Robust Subgame Exploitation in Imperfect Information Games
Opponent exploitation is an important task for players to exploit the weaknesses of others in
games. Existing approaches mainly focus on balancing between exploitation and …
games. Existing approaches mainly focus on balancing between exploitation and …
Online learning with uncertain constraints: cumulative and replenishable violations
M Bernasconi de Luca - 2023 - politesi.polimi.it
Learning how to act optimally in complex environments constitutes a crucial milestone in the
field of artificial intelligence. In recent years, considerable attention has been directed …
field of artificial intelligence. In recent years, considerable attention has been directed …