Going Beyond Linear RL: Sample Efficient Neural Function Approximation

Authors: Baihe Huang, Kaixuan Huang, Sham Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Our first result is a computationally and statistically efficient algorithm in the generative model setting under completeness for two-layer neural networks. Our second result considers this setting but under only realizability of the neural net function class. If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]
Researcher Affiliation Collaboration Baihe Huang1 , Kaixuan Huang2 , Sham M. Kakade3,4 , Jason D. Lee2 Qi Lei2 , Runzhe Wang2 , Jiaqi Yang5 1Peking University 2Princeton University 3Harvard University 4Microsoft Research 5Tsinghua University
Pseudocode Yes Algorithm 1 Learning realizable Q with deterministic transition ... Algorithm 5 Dynamic programming under online RL settings
Open Source Code No If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]
Open Datasets No The paper is theoretical and does not report on experiments using datasets. All experiment-related checklist items are marked as N/A.
Dataset Splits No The paper is theoretical and does not report on experiments using datasets, thus no training/validation/test splits are provided. The checklist indicates '[N/A]' for training details including data splits.
Hardware Specification No If you ran experiments... (d) Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [N/A]
Software Dependencies No The paper is theoretical and does not describe experimental setup requiring specific software dependencies with version numbers. There are no mentions of software versions.
Experiment Setup No If you ran experiments... (b) Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [N/A]