Prospective Side Information for Latent MDPs

Authors: Jeongyeol Kwon, Yonathan Efroni, Shie Mannor, Constantine Caramanis

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We then establish that any sample efficient algorithm must suffer at least Ω(K2/3)-regret, as opposed to standard Ω(K) lower bounds. We design an algorithm with a matching upper bound that depends only polynomially on the problem parameters. In this section, we present our algorithmic results as well as lower bound analysis.
Researcher Affiliation Collaboration 1Wisconsin Institute for Discovery, Wisconsin, USA 2Meta AI, New York, USA 3Electrical Engineering, Technion, Haifa, Israel 4NVIDIA 5Electrical and Computer Engineering, University of Texas at Austin, Texas, USA.
Pseudocode Yes Algorithm 1 Regret Minimization within Πblind, Algorithm 2 Pure Exploration for LMDP-Ψ
Open Source Code No The paper does not contain any statement or link regarding the availability of open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not describe experiments or use any specific dataset.
Dataset Splits No The paper is theoretical and does not describe experiments or specify dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe experiments or specify any hardware used.
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 experiments or provide details on experimental setup, hyperparameters, or training configurations.