Probabilistic Planning with Risk-Sensitive Criterion
Authors: Ping Hou
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this ongoing work, I formally define RS-MDPs and RS-POMDPs and introduce various algorithms for RS-MDPs and RS-POMDPs with different assumptions (e.g., with zero costs and with cost observations). Generally, the DFS and DP style algorithms (include TVIDFS and TVI-DP) are faster than VI and FVI. The reason is that VI and FVI need to perform updates for the entire augmented state or belief state space in every iteration. On the other hand, DFS and DP style algorithms only perform updates for each augmented state or belief state for a minimum number of iterations. |
| 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 algorithms but does not provide pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | No statement about open-source code availability or links to repositories for the described methodology. |
| Open Datasets | No | The paper describes theoretical work and algorithms; it does not mention using any datasets, public or otherwise, for training. |
| Dataset Splits | No | The paper describes theoretical work and algorithms; it does not mention any training, validation, or test dataset splits as it does not involve empirical experiments. |
| Hardware Specification | No | No specific hardware details (like GPU/CPU models, memory amounts, or detailed computer specifications) used for running experiments are mentioned in the paper. |
| Software Dependencies | No | No specific software dependencies with version numbers (e.g., library or solver names with versions) are mentioned in the paper. |
| Experiment Setup | No | The paper describes theoretical work and algorithms; it does not provide details about an experimental setup, such as hyperparameters or training settings. |