Pablo Samuel Castro

Google Scholar

Biography

Pablo Samuel Castro was born and raised in Quito, Ecuador, and moved to Montréal after high school to study at McGill University. For his PhD, he studied reinforcement learning with Doina Precup and Prakash Panangaden at McGill. Castro has been working at Google for over eleven years. He is currently a staff research scientist at Google DeepMind in Montreal, where he conducts fundamental reinforcement learning research and is a regular advocate for increasing LatinX representation in the research community.

He is also an adjunct professor in the Department of Computer Science and Operations Research (DIRO) at Université de Montréal. In addition to his interest in coding, AI and math, Castro is an active musician.

Current Students

Roger Creus-Castanyer

PhD - Université de Montréal

Principal supervisor :

Independent visiting researcher - RWTH Aachen University

Collaborating Alumni - Université de Montréal

Nicola Gauthier

Master's Research - Université de Montréal

Olya Mastikhina

PhD - Université de Montréal

Walter Mayor

Collaborating researcher

Github

Google Scholar

Johan Samir Obando Ceron

PhD - Université de Montréal

Principal supervisor :

PhD - McGill University

Principal supervisor :

PhD - McGill University

Principal supervisor :

Blake Richards

Dhruv Sreenivas

PhD - Université de Montréal

RLiable: Towards Reliable Evaluation & Reporting in Reinforcement Learning

Github

Blog Posts

May 12, 2022

Rishabh Agarwal

Pablo Samuel Castro

Read the article

Publications

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… (see more)) 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 (published)

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 … (see more)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 (published)

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… (see more)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 (accepted)

Training PPO-Clip with Parallelized Data Generation: A Case of Fixed-Point Convergence

Homayoun Honari

Roger Creus Castanyer

Glen Berseth

In recent years, with the increase in the compute power of GPUs, parallelized data collection has become the dominant approach for training … (see more)reinforcement learning (RL) agents. Proximal Policy Optimization (PPO) is one of the widely-used on-policy methods for training RL agents. In this paper, we focus on the training behavior of PPO-Clip with the increase in the number of parallel environments. In particular, we show that as we increase the amount of data used to train PPO-Clip, the optimized policy would converge to a fixed distribution. We use the results to study the behavior of PPO-Clip in two case studies: the effect of change in the minibatch size and the effect of increase in the number of parallel environments versus the increase in the rollout lengths. The experiments show that settings with high-return PPO runs result in slower convergence to the fixed-distribution and higher consecutive KL divergence changes. Our results aim to offer a better understanding for the prediction of the performance of PPO with the scaling of the parallel environments.

2025-06-21

rl-conference.cc/RLC/2025/Workshop/IBRL (published)

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… (see more)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.

2025-05-31

arXiv (published)

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

Aaron Courville

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… (see more)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 (published)

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 … (see more)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 (published)

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… (see more)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 (published)

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… (see more)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.

2025-04-30

ICML.cc/2025/Conference (poster)

proceedings.mlr.press

Don't Flatten, Tokenize! Unlocking the Key to SoftMoE's Efficacy in Deep RL

Ghada Sokar

Johan Obando-Ceron

Aaron Courville

Hugo Larochelle

The use of deep neural networks in reinforcement learning (RL) often suffers from performance degradation as model size increases. While sof… (see more)t mixtures of experts (SoftMoEs) have recently shown promise in mitigating this issue for online RL, the reasons behind their effectiveness remain largely unknown. In this work we provide an in-depth analysis identifying the key factors driving this performance gain. We discover the surprising result that tokenizing the encoder output, rather than the use of multiple experts, is what is behind the efficacy of SoftMoEs. Indeed, we demonstrate that even with an appropriately scaled single expert, we are able to maintain the performance gains, largely thanks to tokenization.

2025-01-21

ICLR.cc/2025/Conference (spotlight)

Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning

Samuel Garcin

Trevor McInroe

Prakash Panangaden

Christopher G. Lucas

David Abel

Stefano V Albrecht

2025-01-21

ICLR.cc/2025/Conference (poster)

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn

Hongyao Tang

Johan Obando-Ceron

Aaron Courville

Glen Berseth

Plasticity, or the ability of an agent to adapt to new tasks, environments, or distributions, is crucial for continual learning. In this pap… (see more)er, we study the loss of plasticity in deep continual RL from the lens of churn: network output variability for out-of-batch data induced by mini-batch training. We demonstrate that (1) the loss of plasticity is accompanied by the exacerbation of churn due to the gradual rank decrease of the Neural Tangent Kernel (NTK) matrix; (2) reducing churn helps prevent rank collapse and adjusts the step size of regular RL gradients adaptively. Moreover, we introduce Continual Churn Approximated Reduction (C-CHAIN) and demonstrate it improves learning performance and outperforms baselines in a diverse range of continual learning environments on OpenAI Gym Control, ProcGen, DeepMind Control Suite, and MinAtar benchmarks.

2024-12-31

ICML (published)