Pablo Samuel Castro

ali.sahebpasand@mila.quebec

johan.ceron@mila.quebec

Doctorat - McGill

Superviseur⋅e principal⋅e :

Doctorat - McGill

Superviseur⋅e principal⋅e :

Blake Richards

Dhruv Sreenivas

Doctorat - UdeM

dhruv.sreenivas@mila.quebec

Site web

Github

Billets de blogue

RLiable: Towards Reliable Evaluation & Reporting in Reinforcement Learning

12 mai 2022

RLiable : pour une évaluation et des rapports plus fiables en apprentissage par renforcement

par

Rishabh Agarwal

Pablo Samuel Castro

Lire l'article

Publications

Discovering Symbolic Cognitive Models from Human and Animal Behavior

Nenad Tomasev

Ankit Anand

Navodita Sharma

Rishika Mohanta

Aparna Dev

Kuba Perlin

Siddhant Jain

Kyle Levin

Noemi Elteto

Will Dabney

Alexander Novikov

Glenn C Turner

Maria K Eckstein

Nathaniel D. Daw

Kevin J Miller

Kim Stachenfeld

Symbolic models play a key role in cognitive science, expressing computationally precise hypotheses about how the brain implements a cogniti… (voir plus)ve process. Identifying an appropriate model typically requires a great deal of effort and ingenuity on the part of a human scientist. Here, we adapt FunSearch (Romera-Paredes et al. 2024), a recently developed tool that uses Large Language Models (LLMs) in an evolutionary algorithm, to automatically discover symbolic cognitive models that accurately capture human and animal behavior. We consider datasets from three species performing a classic reward-learning task that has been the focus of substantial modeling effort, and find that the discovered programs outperform state-of-the-art cognitive models for each. The discovered programs can readily be interpreted as hypotheses about human and animal cognition, instantiating interpretable symbolic learning and decision-making algorithms. Broadly, these results demonstrate the viability of using LLM-powered program synthesis to propose novel scientific hypotheses regarding mechanisms of human and animal cognition.

2025-10-05

Proceedings of the 42nd International Conference on Machine Learning (publié)

proceedings.mlr.press

Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning

Jiashun Liu

Johan Samir Obando Ceron

Han Lu

Yancheng He

Weixun Wang

Wenbo Su

Bo Zheng

Ling Pan

Most recent RL for LLMs (RL4LLM) methods avoid explicit critics, replacing them with average advantage baselines. This shift is largely prag… (voir plus)matic: conventional value functions are computationally expensive to train at LLM scale and often fail under sparse rewards and long reasoning horizons. We revisit this bottleneck from an architectural perspective and introduce Asymmetric Proximal Policy Optimization (AsyPPO), a simple and scalable framework that restores the critics role while remaining efficient in large-model settings. AsyPPO employs a set of lightweight mini-critics, each trained on disjoint prompt shards. This design encourages diversity while preserving calibration, reducing value-estimation bias. Beyond robust estimation, AsyPPO leverages inter-critic uncertainty to refine the policy update: (i) masking advantages in states where critics agree and gradients add little learning signal, and (ii) filtering high-divergence states from entropy regularization, suppressing spurious exploration. After training on open-source data with only 5,000 samples, AsyPPO consistently improves learning stability and performance across multiple benchmarks over strong baselines, such as GRPO, achieving performance gains of more than six percent on Qwen3-4b-Base and about three percent on Qwen3-8b-Base and Qwen3-14b-Base over classic PPO, without additional tricks. These results highlight the importance of architectural innovations for scalable, efficient algorithms.

2025-10-01

ArXiv (prépublication)

arxiv.org

Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning

Ghada Sokar

2025-09-17

NeurIPS.cc/2025/Conference (poster)

The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning

Jiashun Liu

Johan Obando-Ceron

Ling Pan

Off-policy deep reinforcement learning (RL) typically leverages replay buffers for reusing past experiences during learning. This can help i… (voir plus)mprove sample efficiency when the collected data is informative and aligned with the learning objectives; when that is not the case, it can have the effect of "polluting" the replay buffer with data which can exacerbate optimization challenges in addition to wasting environment interactions due to wasteful sampling. We argue that sampling these uninformative and wasteful transitions can be avoided by addressing the sunk cost fallacy, which, in the context of deep RL, is the tendency towards continuing an episode until termination. To address this, we propose learn to stop (LEAST), a lightweight mechanism that enables strategic early episode termination based on Q-value and gradient statistics, which helps agents recognize when to terminate unproductive episodes early. We demonstrate that our method improves learning efficiency on a variety of RL algorithms, evaluated on both the MuJoCo and DeepMind Control Suite benchmarks.

2025-07-14

International Conference on Machine Learning (Accept (poster))

proceedings.mlr.press

The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks

Walter Mayor

Johan Obando-Ceron

The use of parallel actors for data collection has been an effective technique used in reinforcement learning (RL) algorithms. The manner in… (voir plus) which data is collected in these algorithms, controlled via the number of parallel environments and the rollout length, induces a form of bias-variance trade-off; the number of training passes over the collected data, on the other hand, must strike a balance between sample efficiency and overfitting. We conduct an empirical analysis of these trade-offs on PPO, one of the most popular RL algorithms that uses parallel actors, and establish connections to network plasticity and, more generally, optimization stability. We examine its impact on network architectures, as well as the hyper-parameter sensitivity when scaling data. Our analyses indicate that larger dataset sizes can increase final performance across a variety of settings, and that scaling parallel environments is more effective than increasing rollout lengths. These findings highlight the critical role of data collection strategies in improving agent performance.

2025-07-14

International Conference on Machine Learning (Accept (poster))

proceedings.mlr.press

A Geometric Lens on RL Environment Complexity Based on Ricci Curvature

Ali Saheb Pasand

Pouya Bashivan

We introduce Ollivier-Ricci Curvature (ORC) as an information-geometric tool for analyzing the local structure of reinforcement learning (RL… (voir plus)) environments. We establish a novel connection between ORC and the Successor Representation (SR), enabling a geometric interpretation of environment dynamics decoupled from reward signals. Our analysis shows that states with positive and negative ORC values correspond to regions where random walks converge and diverge respectively, which are often critical for effective exploration. ORC is highly correlated with established environment complexity metrics, yet integrates naturally with standard RL frameworks based on SR and provides both global and local complexity measures. Leveraging this property, we propose an ORC-based intrinsic reward that guides agents toward divergent regions and away from convergent traps. Empirical results demonstrate that our curvature-driven reward substantially improves exploration performance across diverse environments, outperforming both random and count-based intrinsic baselines.

2025-06-30

rl-conference.cc/RLC/2025/Workshop/Finding_the_Frame (publié)

What Matters for Maximizing Data Reuse In Value-based Deep Reinforcement Learning

Roger Creus Castanyer

Glen Berseth

A key ingredient for successfully applying deep reinforcement learning to challenging tasks is the effective use of data at scale. Although … (voir plus)originally deep RL algorithms achieved this by storing past experiences collected from a synchronous actor in an external replay memory [DQN; Mnih et al., 2013], follow-up works scaled training by collecting data asynchronously through distributed actors [R2D2; Kapturowski et al., 2018], and more recently by GPU-optimized parallelization [PQN; Gallici et al., 2024]. We argue that DQN, PQN, and R2D2 constitute a group of value-based methods for parallel training and study them to shed light on the dynamics induced by varying data collection schemes. We conduct a thorough empirical study to better understand these dynamics, and propose the Data Replay Ratio as a novel metric for quantifying data reuse. Our findings suggest that maximizing data reuse involves directly addressing the deadly triad: Q-lambda rollouts for reducing the bias from bootstrapping, the use of LayerNorm for stabilizing function approximation, and parallelized data collection for mitigating off-policy divergence.

2025-06-30

rl-conference.cc/RLC/2025/Workshop/Finding_the_Frame (publié)

A Survey of State Representation Learning for Deep Reinforcement Learning

Ayoub Echchahed

Representation learning methods are an important tool for addressing the challenges posed by complex observations spaces in sequential decis… (voir plus)ion making problems. Recently, many methods have used a wide variety of types of approaches for learning meaningful state representations in reinforcement learning, allowing better sample efficiency, generalization, and performance. This survey aims to provide a broad categorization of these methods within a model-free online setting, exploring how they tackle the learning of state representations differently. We categorize the methods into six main classes, detailing their mechanisms, benefits, and limitations. Through this taxonomy, our aim is to enhance the understanding of this field and provide a guide for new researchers. We also discuss techniques for assessing the quality of representations, and detail relevant future directions.

2025-06-22

TMLR (accepté)

Gintare Karolina Dziugaite

Continual Learning in Vision-Language Models via Aligned Model Merging

Ghada Sokar

Anurag Arnab

Ahmet Iscen

Cordelia Schmid

Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors pl… (voir plus)asticity over the stability needed to retain prior knowledge. While existing approaches attempt to mitigate catastrophic forgetting, a bias towards recent tasks persists as they build upon this sequential nature. In this work we present a new perspective based on model merging to maintain stability while still retaining plasticity. Rather than just sequentially updating the model weights, we propose merging newly trained task parameters with previously learned ones, promoting a better balance. To maximize the effectiveness of the merging process, we propose a simple mechanism that promotes learning aligned weights with previous ones, thereby avoiding interference when merging. We evaluate this approach on large Vision-Language Models (VLMs), and demonstrate its effectiveness in reducing forgetting, increasing robustness to various task orders and similarities, and improving generalization.

2025-05-29

ArXiv (prépublication)

arxiv.org

Learning and Controlling Silicon Dopant Transitions in Graphene using Scanning Transmission Electron Microscopy

Max Schwarzer

Jesse Farebrother

Joshua Greaves

Ekin Dogus Cubuk

Rishabh Agarwal

Bellemare Marc-Emmanuel

Sergei Kalinin

Igor Mordatch

Kevin M Roccapriore

We introduce a machine learning approach to determine the transition dynamics of silicon atoms on a single layer of carbon atoms, when stimu… (voir plus)lated by the electron beam of a scanning transmission electron microscope (STEM). Our method is data-centric, leveraging data collected on a STEM. The data samples are processed and filtered to produce symbolic representations, which we use to train a neural network to predict transition probabilities. These learned transition dynamics are then leveraged to guide a single silicon atom throughout the lattice to pre-determined target destinations. We present empirical analyses that demonstrate the efficacy and generality of our approach.

2025-05-19

Advanced Materials Interfaces (publié)

arxiv.org

Multi-Task Reinforcement Learning Enables Parameter Scaling

Reginald McLean

Evangelos Chatzaroulas

J K Terry

Isaac Woungang

Nariman Farsad

Multi-task reinforcement learning (MTRL) aims to endow a single agent with the ability to perform well on multiple tasks. Recent works have … (voir plus)focused on developing novel sophisticated architectures to improve performance, often resulting in larger models; it is unclear, however, whether the performance gains are a consequence of the architecture design or the extra parameters. We argue that gains are mostly due to scale by demonstrating that naively scaling up a simple MTRL baseline to match parameter counts outperforms the more sophisticated architectures, and these gains benefit most from scaling the critic over the actor. Additionally, we explore the training stability advantages that come with task diversity, demonstrating that increasing the number of tasks can help mitigate plasticity loss. Our findings suggest that MTRL's simultaneous training across multiple tasks provides a natural framework for beneficial parameter scaling in reinforcement learning, challenging the need for complex architectural innovations.

2025-05-08

rl-conference.cc/RLC/2025/Conference (accepté)

Optimistic critics can empower small actors

Olya Mastikhina

Dhruv Sreenivas

Actor-critic methods have been central to many of the recent advances in deep reinforcement learning. The most common approach is to use _sy… (voir plus)mmetric_ architectures, whereby both actor and critic have the same network topology and number of parameters. However, recent works have argued for the advantages of _asymmetric_ setups, specifically with the use of smaller actors. We perform broad empirical investigations and analyses to better understand the implications of this and find that, in general, smaller actors result in performance degradation and overfit critics. Our analyses suggest _poor data collection_, due to value underestimation, as one of the main causes for this behavior, and further highlight the crucial role the critic can play in alleviating this pathology. We explore techniques to mitigate the observed value underestimation, which enables further research in asymmetric actor-critic methods.

2025-05-08

rl-conference.cc/RLC/2025/Conference (accepté)