Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty

Authors: Laixi Shi, Eric Mazumdar, Yuejie Chi, Adam Wierman

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Assuming a non-adaptive sampling mechanism from a generative model, we propose a sample-efficient model-based algorithm (DRNVI) with finite-sample complexity guarantees for learning robust variants of various notions of game-theoretic equilibria. We also establish an information-theoretic lower bound for solving RMGs, which confirms the near-optimal sample complexity of DR-NVI with respect to problemdependent factors such as the size of the state space, the target accuracy, and the horizon length.
Researcher Affiliation Academia Laixi Shi 1 Eric Mazumdar 1 Yuejie Chi 2 Adam Wierman 1 1Department of Computing Mathematical Sciences, California Institute of Technology, CA 91125, USA. 2Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
Pseudocode Yes Algorithm 1 Distributionally robust equilibrium value iteration (DR-NVI).
Open Source Code No The paper does not mention providing any open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not conduct experiments with specific datasets. It mentions assuming access to a "generative model" for theoretical sampling, but this is not a publicly available dataset with concrete access information.
Dataset Splits No The paper is theoretical and does not describe empirical experiments involving dataset splits (training, validation, or test data).
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 list any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup, hyperparameters, or training settings for practical implementation or experiments.