Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Ad Hoc Teamwork With Behavior Switching Agents
Authors: Manish Ravula, Shani Alkoby, Peter Stone
IJCAI 2019 | Venue PDF | 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 EMAIL, EMAIL, EMAIL |
| 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. |