Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning

Authors: Anuj Mahajan, Mikayel Samvelyan, Lei Mao, Viktor Makoviychuk, Animesh Garg, Jean Kossaifi, Shimon Whiteson, Yuke Zhu, Animashree Anandkumar

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results in different domains confirm TESSERACT s gains in sample efficiency predicted by the theory. Empirical results in different domains confirm TESSERACT s gains in sample efficiency predicted by the theory.
Researcher Affiliation Collaboration 1University of Oxford 2University College London 3NVIDIA.
Pseudocode Yes Algorithm 1 Model-based Tesseract; Algorithm 2 Model-free Tesseract
Open Source Code No The paper does not provide any statement or link indicating that its source code is open-source or publicly available.
Open Datasets Yes Star Craft Multi-Agent Challenge (SMAC) (Samvelyan et al., 2019)
Dataset Splits No The paper mentions using the Star Craft Multi-Agent Challenge (SMAC) but does not provide specific details on training, validation, and test dataset splits (e.g., percentages or sample counts).
Hardware Specification No The acknowledgements mention a "generous equipment grant from NVIDIA" but do not specify any concrete hardware details such as CPU/GPU models or memory specifications used for the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers used for the experiments.
Experiment Setup No The paper describes the methods and presents empirical results but does not include specific details about experimental setup such as hyperparameter values (e.g., learning rate, batch size) or other system-level training settings in the main text.