The Malmo Platform for Artificial Intelligence Experimentation

Authors: Matthew Johnson, Katja Hofmann, Tim Hutton, David Bignell

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We present Project Malmo an AI experimentation platform built on top of the popular computer game Minecraft, and designed to support fundamental research in artificial intelligence. In this demo we present the Malmo platform and its capabilities.
Researcher Affiliation Industry Microsoft {matjoh,katja.hofmann,a-tihutt,a-dabign}@microsoft.com
Pseudocode No The paper describes the conceptual components and workflow of the Malmo platform but does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes The platform is publicly released as open source software at IJCAI, to support openness and collaboration in AI research.
Open Datasets No The paper describes an experimentation platform and mentions its use with Minecraft, but it does not specify a publicly available or open dataset used for its own evaluation, nor does it provide access information (link, DOI, formal citation) for any specific dataset.
Dataset Splits No The paper presents a platform but does not conduct empirical experiments or report on data-driven results, and therefore does not provide specific dataset split information (percentages, counts, or predefined splits) for training, validation, or testing.
Hardware Specification No The paper describes the Malmo platform but does not provide specific hardware details (e.g., GPU/CPU models, memory amounts, or cloud instance types) used for its development or demonstration.
Software Dependencies No The paper mentions Minecraft and conceptually refers to RLGLue and the Atari emulator Stella, but it does not list specific ancillary software components with version numbers (e.g., Python 3.8, PyTorch 1.9, CPLEX 12.4) needed to replicate the platform's development or experimental environment.
Experiment Setup No The paper describes the components of the Malmo platform that allow for experiment definition (e.g., Mission Spec, Agent Host), but it does not provide specific experimental setup details (like concrete hyperparameter values, training configurations, or system-level settings) for any experiments performed or reported within the paper.