Pablo Samuel Castro
Scholar

Pablo Samuel Castro

Google Scholar ID: jn5r6TsAAAAJ
Google
Reinforcement LearningMachine LearningArtificial IntelligenceCreativityMusic
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
5,678
 
H-index
30
 
i10-index
43
 
Publications
20
 
Co-authors
22
list available
Contact
No contact links provided.
Publications
22 items
Align and Filter: Improving Performance in Asynchronous On-Policy RL
2026
Cited
0
Stable Deep Reinforcement Learning via Isotropic Gaussian Representations
2026
Cited
0
Discovering Differences in Strategic Behavior Between Humans and LLMs
2026
Cited
0
A Comedy of Estimators: On KL Regularization in RL Training of LLMs
2025
Cited
0
The Formalism-Implementation Gap in Reinforcement Learning Research
2025
Cited
0
ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning
2025
Cited
0
Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents
2025
Cited
0
Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning
2025
Cited
0
Resume (English only)
Co-authors
22 total
Marc G. Bellemare
Marc G. Bellemare
Reliant AI
Aaron Courville
Aaron Courville
Professor, DIRO, Université de Montréal, Mila, Cifar CAI chair
Rishabh Agarwal
Rishabh Agarwal
Meta, ex DeepMind, Google Brain
Johan Obando-Ceron
Johan Obando-Ceron
Mila, University of Montreal
Co-author 5
Co-author 5
Co-author 6
Co-author 6
Utku Evci
Utku Evci
Researcher @Google Deepmind
Doina Precup
Doina Precup
DeepMind and McGill University