The Geometry of Robust Value Functions
Authors: Kaixin Wang, Navdeep Kumar, Kuangqi Zhou, Bryan Hooi, Jiashi Feng, Shie Mannor
ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | All proofs and the specifics of MDPs and RMDPs used for illustration can be found in Appendix. Through our analysis, we show that the robust value space is determined by a set of conic hypersurfaces. |
| Researcher Affiliation | Collaboration | 1Institute of Data Science, National University of Singapore, Singapore 2Electrical and Computer Engineering, Technion, Haifa, Israel 3Department of Electrical and Computer Engineering, National University of Singapore, Singapore 4School of Computing, National University of Singapore, Singapore 5Byte Dance, Singapore 6NVIDIA Research, Haifa, Israel. |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not include any explicit statements or links indicating that the source code for the described methodology is publicly available. |
| Open Datasets | No | The paper describes specific MDP and RMDP parameters in Appendix A for illustrative purposes, but these are not publicly available datasets in the traditional sense, nor are they used for training. |
| Dataset Splits | No | The paper is theoretical and does not involve empirical experiments with dataset splits, thus no validation split information is provided. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used, such as GPU or CPU models. It focuses on theoretical analysis and does not mention any computational experiments requiring specific hardware. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers for reproducibility. It primarily focuses on theoretical aspects. |
| Experiment Setup | No | The paper details parameters for illustrative MDPs and RMDPs in Appendix A, but these are for generating figures and are not presented as an 'experimental setup' with hyperparameters or training configurations for an empirical study. |