Learning Rationalizable Equilibria in Multiplayer Games

Authors: Yuanhao Wang, Dingwen Kong, Yu Bai, Chi Jin

ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we first propose a simple yet sample-efficient algorithm for finding a rationalizable action profile in multi-player general-sum games under bandit feedback... We further develop algorithms with the first efficient guarantees for learning rationalizable Coarse Correlated Equilibria (CCE) and Correlated Equilibria (CE).
Researcher Affiliation Collaboration Yuanhao Wang 1, Dingwen Kong 2, Yu Bai3, Chi Jin1 1Princeton University, 2Peking University, 3Salesforce Research
Pseudocode Yes Algorithm 1 Iterative Best Response; Algorithm 2 Hedge for Rationalizable "u03B5"-CCE; Algorithm 3 Adaptive Hedge for Rationalizable "; Algorithm 4 Rationalizable ";
Open Source Code No The paper does not contain any explicit statements about making its source code publicly available or provide a link to a code repository for the described methods.
Open Datasets No The paper focuses on theoretical algorithm design and analysis (sample complexity, proofs) and does not describe experiments using specific, publicly available datasets for training.
Dataset Splits No The paper is theoretical and does not describe empirical experiments involving dataset splits (training, validation, test) for model validation.
Hardware Specification No The paper is theoretical and does not mention any specific hardware (like GPU or CPU models, memory, or cloud instances) used for running experiments.
Software Dependencies No The paper focuses on theoretical algorithms and their mathematical properties. It does not specify any software dependencies with version numbers required to implement or run the proposed algorithms.
Experiment Setup No The paper describes theoretical algorithms and their parameters for analysis, but it does not detail an experimental setup with specific hyperparameters, training configurations, or system-level settings for empirical evaluation.