Ad Hoc Teamwork With Behavior Switching Agents

Authors: Manish Ravula, Shani Alkoby, Peter Stone

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental When evaluating our algorithm on the modified predator prey domain, we find that it outperforms existing Bayesian CPD algorithms. We provide a detailed experimental evaluation of the proposed method in a modified predator-prey domain [Benda et al., 1986].
Researcher Affiliation Academia Manish Ravula , Shani Alkoby and Peter Stone The University of Texas at Austin, Texas, USA manishreddy@utexas.edu, shani@cs.utexas.edu, pstone@cs.utexas.edu
Pseudocode Yes Algorithm 1 MAP Type Estimation, Algorithm 2 Convolutional Changepoint Detection (Conv CPD) for each agent, Algorithm 3 Template for Agent Types
Open Source Code No The paper does not provide any explicit statements about open-sourcing the code for the described methodology or links to a code repository.
Open Datasets No The paper describes a 'modified predator-prey domain' and refers to [Benda et al., 1986] for the original domain, but does not provide concrete access information (link, DOI, specific repository, or explicit statement of public availability) for a dataset used in training.
Dataset Splits No The paper states 'The Conv CPD algorithm is trained with 10,000 samples', but it does not provide specific training/validation/test split percentages, sample counts, or references to predefined splits for reproduction.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory, or cloud instance types) used for running the experiments.
Software Dependencies No The paper mentions using Convolutional Neural Networks and SGD optimizer, but it does not specify version numbers for any software dependencies or libraries.
Experiment Setup Yes The Conv CPD algorithm is trained with 10,000 samples (batch size = 64, learning rate = 0.01, decay = 0.1, optimizer = SGD) involving equal proportions of all classes.