Probabilistic Planning with Risk-Sensitive Criterion

Authors: Ping Hou

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In my work, I introduced various algorithms for RSMDPs with different assumptions... In our recent paper (Hou, Yeoh, and Varakantham 2014), we formally defined Risk-Sensitive MDPs (RS-MDPs) and show that the optimal policy for RS-MDPs is not stationary in the original state space... The overall scope of my thesis is to develop efficient and scalable algorithms to optimize the RS-criterion in probabilistic planning problems.
Researcher Affiliation Academia Ping Hou Department of Computer Science New Mexico State University Las Cruces, NM 88003, USA phou@cs.nmsu.edu
Pseudocode No The paper describes several algorithms (TVI-DP, TVI-DFS, PVI-DP, PO-FVI) but does not provide their pseudocode or formal algorithm blocks.
Open Source Code No The paper does not provide any specific links or explicit statements regarding the availability of source code for the described methodology.
Open Datasets No This paper is theoretical and focuses on algorithm design and research plans. It does not describe experiments that use a specific dataset, nor does it provide access information for any dataset.
Dataset Splits No This paper is theoretical and outlines algorithm design and future research. It does not report on empirical experiments or specify any training, validation, or test dataset splits.
Hardware Specification No This paper describes theoretical algorithms and research plans. It does not report on empirical experiments and therefore does not specify any hardware used.
Software Dependencies No This paper focuses on theoretical algorithm design and research plans. It does not report on empirical experiments and therefore does not specify any software dependencies with version numbers.
Experiment Setup No This paper is theoretical, outlining algorithm design and future research plans. It does not report on empirical experiments or provide specific experimental setup details such as hyperparameters or training configurations.