Equi-Reward Utility Maximizing Design in Stochastic Environments

Authors: Sarah Keren, Luis Pineda, Avigdor Gal, Erez Karpas, Shlomo Zilberstein

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Evaluation shows the feasibility of the approach using standard benchmarks from the probabilistic planning competition and a benchmark we created for a vacuum cleaning robot setting.
Researcher Affiliation Academia Technion Israel Institute of Technology College of Information and Computer Sciences, University of Massachusetts Amherst
Pseudocode Yes Algorithm 1 Best First Design (BFD)
Open Source Code No The paper does not provide any explicit statement about making its source code open, nor does it provide a link to a code repository for its described methodology.
Open Datasets Yes We used five PPDDL domains from the probabilistic tracks of the sixth and eighth International Planning Competition2 (IPPC06 and IPPC08)... 2http://icaps-conference.org/index.php/main/competitions
Dataset Splits No The paper does not specify explicit training, validation, or test dataset splits (e.g., percentages or sample counts) for reproducibility, beyond mentioning using instances from known competitions.
Hardware Specification Yes Each problem was tested on a Intel(R) Xeon(R) CPU X5690 machine with a budget of 1, 2 and 3.
Software Dependencies No The paper mentions using tools like 'PPDDL notation', 'LAO*', and the 'FF classical planner', but it does not provide specific version numbers for these or other software dependencies.
Experiment Setup Yes Design actions were assigned a cost of 10 4, and problems were solved using LAO* [Hansen and Zilberstein, 1998] with convergence error bound of 10 6. Each run had a 30 minutes time limit.