Portrait of Aaron Courville

Aaron Courville

Core Academic Member
Canada CIFAR AI Chair
Full Professor, Université de Montréal
Research Topics
Computer Vision
Deep Learning
Efficient Communication in General Sum Game
Game Theory
Generative Models
Multi-Agent Systems
Natural Language Processing
Reinforcement Learning
Representation Learning

Biography

Aaron Courville is a professor in the Department of Computer Science and Operations Research (DIRO) at Université de Montréal and Scientific Director of IVADO. He has a PhD from the Robotics Institute, Carnegie Mellon University.

Courville was an early contributor to deep learning: he is a founding member of Mila – Quebec Artificial Intelligence Institute. Together with Ian Goodfellow and Yoshua Bengio, he co-wrote the seminal textbook on deep learning.

His current research focuses on the development of deep learning models and methods. He is particularly interested in reinforcement learning, multi-agent reinforcement learning, deep generative models and reasoning.

Courville holds a Canada CIFAR AI Chair and a Canada Research Chair in Systematic Generalization. His research has been supported by Microsoft Research, Samsung, Hitachi, Meta, Sony (Research Award) and Google (Focused Research Award).

Current Students

PhD - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
PhD - Université de Montréal
PhD - Université de Montréal
Co-supervisor :
PhD - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
Co-supervisor :
PhD - Université de Montréal
Master's Research - Université de Montréal
PhD - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
PhD - Université de Montréal

Publications

Representation Learning Enables Scalable Multitask Deep Reinforcement Learning
Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achie… (see more)ve strong performance, they rely on planning and complex training pipelines, making it unclear which components are essential for scalability. We revisit this question and argue that the primary driver of scalable multitask RL is not model-based control, but \emph{representation learning}. In particular, we show that combining predictive, model-based representations with high-capacity value function approximation is sufficient to achieve strong performance, even without planning. We evaluate a simple model-free algorithm, MR.Q, coupled with auxiliary predictive objectives into a scalable actor-critic architecture. This approach outperforms a recent world-model-based method and a range of deep RL baselines across a diverse suite of multitask continuous control tasks, while significantly reducing computational overhead and improving wall-clock efficiency. We observe consistent improvements with increased model capacity and show through ablations that predictive representation learning is critical for performance.
Training Stability under Adaptive Curricula
Johan Obando-Ceron
Michael Dennis
Unsupervised Environment Design (UED) approaches train reinforcement learning (RL) agents on diverse curricula that may evolve with their ca… (see more)pabilities. While prior work has largely focused on how these curricula are constructed, we study whether their students remain trainable under the resulting distributions. Across multiple UED mechanisms, environment complexities, and extended training horizons, we identify recurring learner-side pathologies, including parameter growth, degraded value--outcome ordering, and loss of representational diversity, that accompany stagnation and performance degradation. These findings connect limitations in UED to optimization failures previously identified in conventional deep RL, while showing how adaptive curricula couple the learner's optimization state to its future training distribution. Controlled interventions show that mitigating selected pathologies improves learning. Stabilizing the learner improves long-horizon performance and zero-shot generalization without changing the curriculum rule or increasing environment interaction. Our results establish learner trainability as a complementary design principle for UED. Effective curricula require students that remain capable of learning from the distributions they produce.
Learning Robust Social Strategies with Large Language Models
As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent … (see more)interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual incentives can undermine collective welfare. While reinforcement learning (RL) has been effective for aligning large language models (LLMs) in the single-agent regime, prior small-network results suggest that standard RL in multi-agent settings often converges to defecting, self-interested policies. We show the same effect in LLMs: despite cooperative priors, RL-trained LLM agents develop opportunistic behaviour that can exploit even advanced models. To address this tendency of RL to converge to poor equilibria, we adapt a recent opponent-learning awareness algorithm, Advantage Alignment, to fine-tune LLMs toward multi-agent cooperation and robustness against exploitation. We then introduce a group-relative baseline that simplifies advantage computation in iterated games, enabling multi-agent training at LLM scale. We also contribute a novel social dilemma environment, Trust-and-Split, which requires natural language communication to achieve high collective welfare. Across a wide range of social dilemmas, policies learned with Advantage Alignment achieve higher collective payoffs while remaining robust against exploitation by greedy agents.
On the Limits of Test-Time Compute for Self-Evaluation
Self-verification and aggregation have emerged as popular approaches for bridging the gap between pass@1 and pass@N. However, increasing the… (see more) number of candidates does not consistently narrow the gap between final-answer accuracy and pass@N. To understand this limitation, we use ranking error to measure how reliably models distinguish their correct generations from incorrect ones. We show that ranking error admits a bias-variance decomposition, with both components shaped by algorithmic design choices and inference compute. Across our experiments, additional compute reduces variance, while bias initially decreases before approaching a plateau. Guided by this analysis, we introduce Scorpio, a simple and general method that jointly scores randomly grouped candidates. Across math, code, and puzzle benchmarks, Scorpio improves verification, tree search, and aggregation. For verification, Scorpio improves accuracy over the strongest baseline by up to 7 percentage points while matching or exceeding that baseline's peak accuracy with 17-42% lower inference cost. For tree search, using Scorpio to score partial solutions and select the final answer improves accuracy by up to 10 percentage points over prior methods. Finally, Scorpio improves the scaling of aggregation-based methods by 11 percentage points on coding tasks.
Freeze, Don't Clone: Fine-Tuning with Expressive Policies Without Retaining Offline Data
Sami Nur Islam
Johan Obando-Ceron
Offline-to-online reinforcement learning uses offline pretraining to accelerate subsequent online learning. While many methods assume the of… (see more)fline dataset remains available throughout fine-tuning, there are many settings where this is not the case. Prior work attributes failures in this setting primarily to critic recalibration under distribution shift. We identify a complementary actor-side failure: once the offline data disappears, continued behavioral cloning (BC) no longer preserves the offline behavior distribution and instead refits the behavioral model to the agent's limited, and nonstationary, online experience. We demonstrate that stopping online behavioral fitting while preserving the pretrained expressive prior substantially improves no-retention fine-tuning across implicit flow Q-learning (IFQL), flow Q-learning (FQL), and action-chunked RL (QC) on seven OGBench domains. We trace this failure to a behavioral feedback loop: continuing online behavioral cloning rapidly erases the pretrained prior, inducing representational collapse and action diversity loss that starves the critic of useful exploration. Freezing the prior breaks this cycle, preserving offline coverage while allowing value learning to drive continuous improvement.
FeaTok: Feature-Loss Tokenization for Image Generation
Zhang Xiaofeng
Samuel Lavoie
Nicolas Beltran-Velez
Jianhao Yuan
Felix Friedrich
Jakob Verbeek
Michal Drozdzal
Adriana Romero-Soriano
Discrete image generators learn the distribution of tokens produced by an image tokenizer. These token representations should be easy for ge… (see more)nerators to model, not merely enable faithful image reconstruction. Yet these tokenizers are commonly trained to reconstruct pixels, which prioritizes low-level fidelity and may disrupt representation structure useful for generation. Motivated by feature-predictive self-supervised learning, we introduce feature-loss tokenization (FeaTok), which trains discrete tokens by reconstructing pretrained features rather than pixels. Ablations across SigLIP, SigLIP2, DINOv2, and DINOv3 show better generative performance with FeaTok. In class-conditional generation, FeaTok advances the quality-compute Pareto frontier, reducing gFDr6 at 256x256 by up to 29 percent over the strongest discrete baselines and outperforming the strongest unguided continuous baseline (RAEv2) with 38 times less sampling compute. FeaTok also achieves higher human-preference reward-model scores than prior art without reward-based training and surpasses continuous and discrete text-conditional baselines on three benchmarks with only 500 fine-tuning updates after pre-training.
GitSwarm: Decentralized Compounding Inference
Ankur Samanta
Paras Dahal
Mikhail Plekhanov
Carole-Jean Wu
Scott Yih
Remi Munos
Rob Fergus
Jakob Foerster
Ruslan Salakhutdinov
Sanjeev Arora
Jason Weston
Long-horizon problem solving and scientific research require computation to accumulate across successive attempts. Partial solutions, experi… (see more)mental findings, and unsuccessful approaches can inform later work, yet most inference-time computation is organized around individual trajectories or candidates rather than a persistent body of reusable work. We call this paradigm compounding inference: organizing inference-time computation so that intermediate work persists and can be inspected, extended, combined, or challenged by subsequent computation. We instantiate compounding inference in GitSwarm, an asynchronous system where homogeneous agents independently decide how to advance a task while collaborating through structured persistent memory. Agents explore, experiment, verify, refine, and synthesize previous work in a shared, branch-able Git repository. Atomic commits preserve intermediate artifacts, while explicit semantic dependencies record how later contributions build on work across branches. We evaluate GitSwarm on long-horizon problem solving and sustained GPU-backed experimental research. On IMOProofBench-Advanced, GitSwarm solves all 30 problems in one run using GPT-5.5. On ProgramBench, it achieves a
V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control
Donghu Kim
Youngdo Lee
Hojoon Lee
Johan Obando-Ceron
Byungkun Lee
Jaegul Choo
Clare Lyle
Improving sample efficiency remains a core challenge in reinforcement learning (RL), especially in real-world settings like robotics, where … (see more)data collection is costly. This challenge is pronounced in visual RL, where high-dimensional inputs often obscure learning signals. While prior work in visual RL has focused on algorithmic solutions, such as better dynamics models or exploration strategies, recent advances in state-based RL show that architectural design alone can lead to significant gains in sample efficiency. This raises an important question: Can these architectural principles transfer to visual RL? In response, we introduce V-Simba, a simple yet effective visual RL architecture inspired by the Simba architecture from state-based RL. Built on top of Soft Actor-Critic (SAC) with data augmentation, V-Simba modifies the architecture by adding normalization layers to stabilize training and using pointwise convolutions to reduce computation. Despite its simplicity, V-Simba matches or outperforms the state-of-the-art methods across the DMC, Adroit, and Meta-World benchmarks, while being more computationally efficient than DrQ-v2. We make our code publicly available at https://github.com/DAVIAN-Robotics/V-Simba.
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
Andrei Liviu Nicolicioiu
On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student, with the teacher conditione… (see more)d on a correct demonstration to provide dense token-level feedback. We show that this could come at a hidden cost: rollout diversity decreases and pass@k curves flatten (i.e., generating more rollouts fails to improve accuracy). We trace this to compounding biases in the design of self-distillation with sampled demonstrations. The teacher scores each student rollout while conditioned on a sampled correct rollout, channeling its feedback through the model's own biases. We theoretically analyze the optimal self-distillation policy and show that it tilts the base distribution by a pointwise conditional mutual information score between the student's rollout and the correct rollout used as context. Unlike the ideal optimal on-policy reinforcement learning (RL), which preserves probability ratios among equally correct rollouts, self-distillation can amplify existing probability gaps, concentrating mass on already-dominant modes. On a controlled graph path-finding task and science question-answering benchmarks, self-distilled models match or exceed RL on average performance but exhibit substantially lower \textit{functional} and \textit{semantic} diversity, failing on out-of-distribution settings that require diverse strategies.
Data Selection Through Iterative Self-Filtering for Vision-Language Settings
Andrei Liviu Nicolicioiu
Sarvjeet Singh Ghotra
Morgane M. Moss
The availability of large amounts of clean data is paramount to training neural networks. However, at large scales, manual oversight is impr… (see more)actical, resulting in sizeable datasets that can be very noisy. Attempts to mitigate this obstacle to producing performant vision-language models have so far involved heuristics, curated reference datasets, and using pre-trained models. Here we propose a novel, bootstrapped method in which a CLIP model is trained on an evolving, self-selected dataset. This evolving dataset constitutes a balance of filtered, highly probable clean samples as well as diverse samples from the entire distribution. Our proposed Self-Filtering method iterates between training the model and selecting a subsequently improved data mixture. Training on vision-language datasets filtered by the proposed approach improves downstream performance without the need for additional data or pre-trained models.
One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective
Juan Agustin Duque
Sergio García-Heredia
Vinicius Hernandes
Eliška Greplová
Thomas Spriggs
Anna Dawid
Neural quantum states (NQS) provides a flexible and scalable framework for approximating quantum many-body wavefunctions. Among NQS paramete… (see more)rizations, autoregressive models are especially attractive because they enable exact, independent sampling from the Born distribution, avoiding the autocorrelation and mixing issues of Markov chain methods. Yet their optimization remains comparatively underexplored: Adam is a scalable method but ignores function space geometry, while stochastic reconfiguration is principled but costly and numerically fragile in large models. To address this gap, we show that variational energy minimization can be viewed as an advantage policy-gradient problem over the Born distribution, motivating trust-region optimization for NQS training. We introduce \emph{Proximal Wavefunction Optimization} (PWO), a trust-region algorithm that clips probability-ratio changes in the amplitude channel and wrapped phase increments in the phase channel. PWO avoids explicit matrix inversion, reuses samples across inner updates, and preserves the scalability of first-order optimization. Across Ising, Heisenberg, and frustrated
Why Open Source? A Game-Theoretic Analysis of the AI Race
In recent years, with the advancement of frontier AI, we have observed certain dynamics in open-sourcing and closed-sourcing decisions. We p… (see more)ropose a game-theoretic model to analyze these dynamics in the current landscape of the AI race. Our model builds on an R&D race framework under a winner-takes-all setting, and it accounts for the cases where the players' actions can be either discrete or continuous (i.e., partial open-sourcing, such as open weights). We show that determining the existence of a discrete pure non-trivial Nash equilibrium is NP-hard in general but that we can transform the discrete Nash existence computation into a MIP (Mixed-Integer Programming) problem, making it tractable for small instances using a standard MIP solver. Next, we show the existence and tractability of pure Nash equilibria in the continuous version of our problem, leveraging standard convex analysis results, and constructing an equivalent MIP formulation. Throughout this work, we leverage both our main technical results as well as surrounding technical analysis, to derive socially relevant insights that we believe can serve both to understand already existing decisions and dynamics and to potentially inform new policies.