Disentangling Reafferent Effects by Doing Nothing

Authors: Benedict Wilkins, Kostas Stathis

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental Evaluation Alg. 1 is applied to three different environments. To demonstrate the effectiveness and general applicability of our approach, we perform a number of experiments. Each showcases, or has a parallel with, an important concept or experiment performed in related fields.
Researcher Affiliation Academia Benedict Wilkins, Kostas Stathis Department of Computer Science, Royal Holloway University of London benrjw@gmail.com, kostas.stathis@rhul.ac.uk
Pseudocode Yes Algorithm 1: Estimating Effects via SGD
Open Source Code Yes All code and data is publicly available1. 1https://github.com/Benedict Wilkins/disentangling-reafference
Open Datasets Yes Alg. 1 is applied to three different environments. ... (i) Cartpole ... (ii) Atari Freeway ... (iii) Artificial Ape ... (Wilkins and Stathis 2022).
Dataset Splits No The paper does not explicitly provide training/validation/test dataset splits needed to reproduce the experiment.
Hardware Specification No The paper does not explicitly describe the specific hardware used to run its experiments.
Software Dependencies No The paper mentions software components like 'neural network' but does not provide specific version numbers for any software dependencies.
Experiment Setup No Training and model details for each experiment, as well as additional experiments are presented in the supplementary material. The main text does not provide specific hyperparameters or system-level training settings.