A Distributional Framework for Risk-Sensitive End-to-End Planning in Continuous MDPs

Authors: Noah Patton, Jihwan Jeong, Mike Gimelfarb, Scott Sanner9894-9901

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate and compare RAPTOR on three highly stochastic MDPs, including nonlinear navigation, HVAC control, and linear reservoir control, demonstrating the ability of RAPTOR to manage risk in complex continuous domains according to different notions of risk-sensitive utility.
Researcher Affiliation Collaboration Department of Mechanical and Industrial Engineering, University of Toronto... Vector Institute, Toronto, Canada.
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks clearly labeled as such.
Open Source Code No The paper does not provide any concrete statements or links regarding the availability of its source code.
Open Datasets No The paper describes problem domains (Navigation, Reservoir Control, HVAC Control) and how data is modeled or generated within these domains (e.g., normally distributed noise, exponentially-distributed random variable for rainfall), but does not refer to or provide access to any specific, pre-existing publicly available datasets.
Dataset Splits No The paper does not provide specific dataset split information (e.g., percentages, sample counts, or explicit mention of training, validation, or test sets) needed for data partitioning.
Hardware Specification No The paper vaguely mentions "on a consumer-grade PC" but does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts).
Software Dependencies No The paper mentions "Py Torch" and "Adam as the optimizer" but does not provide specific version numbers for these or any other software dependencies.
Experiment Setup No The paper mentions using "Adam as the optimizer and selected the learning rates according to a grid search" but states that "further experimental details" are in the Appendix, which is not provided, thus specific setup details are missing from the main text.