Abstracting Complex Domains Using Modular Object-Oriented Markov Decision Processes
Authors: Shawn Squire, Marie desJardins
AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We present an initial proposal for modular objectoriented MDPs, an extension of OO-MDPs that abstracts complex domains that are partially observable and stochastic with multiple goals. Modes reduce the curse of dimensionality by reducing the number of attributes, objects, and actions into only the features relevant for each goal. These modes may also be used as an abstracted domain to be transferred to other modes or to another domain. |
| Researcher Affiliation | Academia | Shawn Squire and Marie des Jardins University of Maryland, Baltimore County 1000 Hilltop Circle, Baltimore, MD 21250 ssquire1, mariedj@umbc.edu |
| Pseudocode | No | The paper describes conceptual steps for learning a mode, such as 'Learning a mode begins with finding Att(C) and O . First, an optimal policy, π, is assumed to exist...', but these are descriptive paragraphs and not structured pseudocode or an algorithm block. |
| Open Source Code | No | The paper does not provide any specific link or statement about open-source code availability for the described methodology. |
| Open Datasets | No | The paper does not describe any experiments or refer to any datasets used for training. |
| Dataset Splits | No | The paper does not describe any experiments or provide details about dataset splits for training, validation, or testing. |
| Hardware Specification | No | The paper is theoretical and does not describe any experimental setup or specific hardware used. |
| Software Dependencies | No | The paper is theoretical and does not mention any specific software dependencies or versions. |
| Experiment Setup | No | The paper is a theoretical proposal and does not include details on an experimental setup, hyperparameters, or training configurations. |