Learning in POMDPs is Sample-Efficient with Hindsight Observability

Authors: Jonathan Lee, Alekh Agarwal, Christoph Dann, Tong Zhang

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We introduce new algorithms for the tabular and function approximation settings that are provably sample-efficient with hindsight observability, even in POMDPs that would otherwise be statistically intractable. We give a lower bound showing that the tabular algorithm is optimal in its dependence on latent state and observation cardinalities.
Researcher Affiliation Collaboration 1Stanford University 2Google Research 3HKUST.
Pseudocode Yes Algorithm 1 Hindsight OPtimism with Bonus (HOP-B) ... Algorithm 2 Hindsight OPtimism with Version spaces(HOP-V)
Open Source Code No The paper does not provide an explicit statement or link for open-sourcing code for the described methodology.
Open Datasets No The paper is theoretical and does not report on empirical experiments using specific datasets for training.
Dataset Splits No The paper is theoretical and does not report on empirical experiments, thus no dataset splits for validation are specified.
Hardware Specification No The paper is theoretical and does not report on empirical experiments, thus no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not report on empirical experiments, thus no software dependencies with version numbers are specified.
Experiment Setup No The paper is theoretical and does not report on empirical experiments, thus no experimental setup details like hyperparameters are provided.