reproducibilityindex.ai

On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning

Authors: Rohan Subramani, Marcus Williams, Max Heitmann, Halfdan Holm, Charlie Griffin, Joar Max Viktor Skalse

Reproducibility Variable	Result	LLM Response
Research Type	Theoretical	All of our results are theoretical. All proofs can be found in Appendix B.
Researcher Affiliation	Academia	Rohan Subramania,b, , Marcus Williamsa, , Max Heitmanna,c, , Halfdan Holma, Charlie Griffina,c, Joar Skalsea,c a AI Safety Hub, b Columbia University, c University of Oxford *Equal contribution. Correspondence to Rohan Subramani at rs4126@columbia.edu.
Pseudocode	No	The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code	No	The paper does not provide concrete access to source code for the methodology described.
Open Datasets	No	All of our results are theoretical. All proofs can be found in Appendix B. No datasets were used for training.
Dataset Splits	No	All of our results are theoretical. All proofs can be found in Appendix B. No dataset split information is provided as no experiments were conducted.
Hardware Specification	No	All of our results are theoretical. All proofs can be found in Appendix B. No hardware specifications are provided as no experiments were conducted.
Software Dependencies	No	All of our results are theoretical. All proofs can be found in Appendix B. No specific ancillary software details are provided as no experiments were conducted.
Experiment Setup	No	All of our results are theoretical. All proofs can be found in Appendix B. No experimental setup details are provided as no experiments were conducted.