François Paugam

AI Models of Human Brain and Behaviour During Naturalistic Videogame Play

Yann Harel

André Cyr

Basile Pinsard

Julie Boyle

Slides of the presentation given at the Montreal Artificial Intelligence and Neuroscience (MAIN) conference, December 2025, by Lune Bellec. … (voir plus)A video recording of the presentation is available on youtube.

2025-12-11

Zenodo (inconnu)

doi.org

Training neural networks from scratch in a videogame leads to brittle brain encoding

Basile Pinsard

Recent brain-encoding studies using videogame tasks suggest that the training objective of an artificial neural network plays a central role… (voir plus) in how well the network’s representations align with brain activity. This study investigates the alignment of artificial neural network activations with brain activity elicited by a video game task using models trained from scratch in controlled settings. We specifically compared three model training objectives: reinforcement learning, imitation learning, and a vision task, while accounting for other potential factors which may impact performance such as training data and model architecture. We tested models on brain encoding, i.e. their ability to predict functional magnetic resonance imaging (fMRI) signals acquired while human subjects played different levels of the video game Super Mario Bros. When tested on new playthroughs from the game levels seen at training, the reinforcement learning objective had a small but significant advantage in brain encoding, followed by the imitation learning and vision models. We hypothesized that brain-aligned representations would emerge only in task-competent models, and that the specific brain regions well encoded by a model would depend on the nature of the task it was trained on. While brain encoding did improve during model training, even an untrained model with matching architecture approached the performance of the best models. Contrary to our hypotheses, no model layers or specific training objectives aligned preferentially with specific brain areas. Large performance gaps also persisted in fully trained models across game levels, both those seen during training and entirely novel ones. Overall, even though reinforcement learning presented a small advantage to train brain encoding models for videogame data, all tested brain encoding models exhibited brittle performance with limited generalization both within- and out-of-distribution. Overall, our results suggest that training small artificial models from scratch is not sufficiently reliable, and that incorporating pretrained models such as foundation vision–action models may ultimately be necessary to support robust inferences about brain representations.

2025-12-01

bioRxiv (prépublication)

doi.org

Human-AI Alignment of Learning Trajectories in Video Games: a continual RL benchmark proposal

Yann Harel

Lune P Bellec

François Paugam

Hugo Delhaye

Audrey Durand

We propose a design for a continual reinforcement learning (CRL) benchmark called GHAIA, centered on human-AI alignment of learning trajecto… (voir plus)ries in structured video game environments. Using \textit{Super Mario Bros.} as a case study, gameplay is decomposed into short, annotated scenes organized into diverse task sequences based on gameplay patterns and difficulty. Evaluation protocols measure both plasticity and stability, with flexible revisit and pacing schedules. A key innovation is the inclusion of high-resolution human gameplay data collected under controlled conditions, enabling direct comparison of human and agent learning. In addition to adapting classical CRL metrics like forgetting and backward transfer, we introduce semantic transfer metrics capturing learning over groups of scenes sharing similar game patterns. We demonstrate the feasibility of our approach on human and agent data, and discuss key aspects of the first release for community input.

2025-06-19

rl-conference.cc/RLC/2025/Workshop/RLVG (accepté)

openreview.net

Behavioral Imitation with Artificial Neural Networks Leads to Personalized Models of Brain Dynamics During Videogame Play

Anirudha Kemtur

François Paugam

Basile Pinsard

Yann Harel

Pravish Sainath

Maximilien Le Clei

Julie Boyle

Karim Jerbi

Pierre Bellec

Videogames provide a promising framework to understand brain activity in a rich, engaging, and active environment, in contrast to mostly pas… (voir plus)sive tasks currently dominating the field, such as image viewing. Analyzing videogames neuroimaging data is however challenging, and relies on time-intensive manual annotations of game events, based on somewhat arbitrary rules. Here, we introduce an innovative approach using Artificial Neural networks (ANN) and brain encoding techniques to generate activation maps associated with videogame behaviour using functional magnetic resonance imaging (fMRI). As individual behavior is highly variable across subjects in complex environments, we hypothesized that ANNs need to account for subject-specific behavior to properly capture brain dynamics. In this study, we used data collected while subjects played Shinobi III: Return of the Ninja Master (Sega, 1993), an action-platformer videogame. Using imitation learning, we trained an ANN to play the game while closely replicating the unique gameplay style of individual participants. We found that hidden layers of our imitation learning model successfully encoded task-relevant neural representations, and predicted individual brain dynamics with higher accuracy than models trained on other subjects’ gameplay. Individual-specific models also outperformed a number of baselines to predict brain activity, such as pixel inputs, or button presses. The highest correlations between layer activations and brain signals were observed in biologically plausible brain areas, i.e. somatosensory, attention, and visual networks. Our results demonstrate that training subject-specific ANNs can successfully uncover brain correlates of complex behaviour. This new method combining imitation learning, brain imaging, and videogames opens new research avenues to study decision-making and psychomotor task solving in naturalistic and complex environments.

2024-07-31

bioRxiv (prépublication)

doi.org

Continuous evaluation of denoising strategies in resting-state fMRI connectivity using fMRIPrep and Nilearn

Hao-Ting Wang

Steven L. Meisler

Hanad Sharmarke

Natasha Clarke

Nicolas Gensollen

Christopher J. Markiewicz

François Paugam

Bertrand Thirion

Pierre Bellec

Reducing contributions from non-neuronal sources is a crucial step in functional magnetic resonance imaging (fMRI) connectivity analyses. Ma… (voir plus)ny viable strategies for denoising fMRI are used in the literature, and practitioners rely on denoising benchmarks for guidance in the selection of an appropriate choice for their study. However, fMRI denoising software is an ever-evolving field, and the benchmarks can quickly become obsolete as the techniques or implementations change. In this work, we present a denoising benchmark featuring a range of denoising strategies, datasets and evaluation metrics for connectivity analyses, based on the popular fMRIprep software. The benchmark prototypes an implementation of a reproducible framework, where the provided Jupyter Book enables readers to reproduce or modify the figures on the Neurolibre reproducible preprint server (https://neurolibre.org/). We demonstrate how such a reproducible benchmark can be used for continuous evaluation of research software, by comparing two versions of the fMRIprep. Most of the benchmark results were consistent with prior literature. Scrubbing, a technique which excludes time points with excessive motion, combined with global signal regression, is generally effective at noise removal. Scrubbing was generally effective, but is incompatible with statistical analyses requiring the continuous sampling of brain signal, for which a simpler strategy, using motion parameters, average activity in select brain compartments, and global signal regression, is preferred. Importantly, we found that certain denoising strategies behave inconsistently across datasets and/or versions of fMRIPrep, or had a different behavior than in previously published benchmarks. This work will hopefully provide useful guidelines for the fMRIprep users community, and highlight the importance of continuous evaluation of research methods.

2024-03-17

PLOS Computational Biology (publié)

doi.org

A benchmark of individual auto-regressive models in a massive fMRI dataset

François Paugam

Basile Pinsard

Guillaume Lajoie

Pierre Bellec

Dense functional magnetic resonance imaging datasets open new avenues to create auto-regressive models of brain activity. Individual idiosyn… (voir plus)crasies are obscured by group models, but can be captured by purely individual models given sufficient amounts of training data. In this study, we compared several deep and shallow individual models on the temporal auto-regression of BOLD time-series recorded during a natural video-watching task. The best performing models were then analyzed in terms of their data requirements and scaling, subject specificity, and the space-time structure of their predicted dynamics. We found the Chebnets, a type of graph convolutional neural network, to be best suited for temporal BOLD auto-regression, closely followed by linear models. Chebnets demonstrated an increase in performance with increasing amounts of data, with no complete saturation at 9 h of training data. Good generalization to other kinds of video stimuli and to resting-state data marked the Chebnets’ ability to capture intrinsic brain dynamics rather than only stimulus-specific autocorrelation patterns. Significant subject specificity was found at short prediction time lags. The Chebnets were found to capture lower frequencies at longer prediction time lags, and the spatial correlations in predicted dynamics were found to match traditional functional connectivity networks. Overall, these results demonstrate that large individual functional magnetic resonance imaging (fMRI) datasets can be used to efficiently train purely individual auto-regressive models of brain activity, and that massive amounts of individual data are required to do so. The excellent performance of the Chebnets likely reflects their ability to combine spatial and temporal interactions on large time scales at a low complexity cost. The non-linearities of the models did not appear as a key advantage. In fact, surprisingly, linear versions of the Chebnets appeared to outperform the original non-linear ones. Individual temporal auto-regressive models have the potential to improve the predictability of the BOLD signal. This study is based on a massive, publicly-available dataset, which can serve for future benchmarks of individual auto-regressive modeling.

2023-12-31

Imaging Neuroscience (publié)

doi.org

AI-based modeling of brain and behavior: Combining neuroimaging, imitation learning and video games

Anirudha Kemtur

Basile Pinsard

Yann Harel

Julie Boyle