Sample-Efficient Reinforcement Learning of Partially Observable Markov Games

Authors: Qinghua Liu, Csaba Szepesvari, Chi Jin

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This work is purely theoretical and we do not anticipate any potential negative social impacts. Did you run experiments? [N/A]
Researcher Affiliation Collaboration Qinghua Liu Princeton University qinghual@princeton.edu Csaba Szepesvári Deep Mind and University of Alberta szepesva@ualberta.ca Chi Jin Princeton University chij@princeton.edu
Pseudocode Yes Algorithm 1 OMLE-Equilibrium, Subroutine 1 Optimistic_Equilibrium(B), Algorithm 2 multi-step OMLE-Equilibrium, Algorithm 3 OMLE-Adversary
Open Source Code No The paper is purely theoretical and does not provide any statement or link regarding the release of source code.
Open Datasets No The paper is purely theoretical and does not use or describe any dataset, public or otherwise.
Dataset Splits No The paper is purely theoretical and does not describe any dataset splits for training, validation, or testing.
Hardware Specification No The paper is purely theoretical and does not mention any hardware specifications for running experiments.
Software Dependencies No The paper is purely theoretical and does not mention specific software dependencies with version numbers for running experiments.
Experiment Setup No The paper is purely theoretical and focuses on algorithm design and theoretical guarantees, thus it does not include details on experimental setup such as hyperparameters or system-level training settings.