Provably Efficient Algorithms for Multi-Objective Competitive RL

Authors: Tiancheng Yu, Yi Tian, Jingzhao Zhang, Suvrit Sra

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This work provides the first provably efficient algorithms for vector-valued Markov games and our theoretical guarantees are near-optimal.
Researcher Affiliation Academia Tiancheng Yu 1 Yi Tian 1 Jingzhao Zhang 1 Suvrit Sra 1 1Department of EECS, MIT, Cambridge, USA. Correspondence to: Suvrit Sra <suvrit@mit.edu>.
Pseudocode Yes Algorithm 1 Multi-objective Meta-algorithm (MOMA) Algorithm 2 VI-Hoeffding (VI-HOEFFDING) Algorithm 3 VI-BERNSTEIN
Open Source Code No The paper does not contain any statements about releasing source code, nor does it provide links to any code repositories for the described methodology.
Open Datasets No The paper focuses on theoretical algorithms and their guarantees and does not involve experiments with specific datasets, therefore no public dataset information is provided.
Dataset Splits No The paper is theoretical and does not conduct experiments involving dataset splits.
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for running experiments.
Software Dependencies No The paper is theoretical and does not mention any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe a concrete experimental setup with hyperparameters or training configurations.