Pablo Samuel Castro

Paper: arxiv.org/abs/2606.05555 Code: github.com/johanobandoc... Thanks for reading! If you're interested in multitask RL, representation learning, or scalable reinforcement learning, we'd love to hear your thoughts and feedback. I'll also be at #ICML2026 next week 🇰🇷

Representation Learning Enables Scalable Multitask Deep Reinforcement Learning arxiv.org

Paper: arxiv.org/abs/2606.05555 Code: github.com/johanobandoc... Thanks for reading! If you're interested in multitask RL, representation learning, or scalable reinforcement learning, we'd love to hear your thoughts and feedback. I'll also be at #ICML2026 next week 🇰🇷

GitHub - johanobandoc/ScaleMRL: Code for "Representation Learning Enables Scalable Multitask Deep Reinforcement Learning" github.com

I'm excited to share our latest work “Representation Learning Enables Scalable Multitask Deep Reinforcement Learning”. In this work, we revisit a fundamental question in reinforcement learning: What if representation learning was the key ingredient behind scalable RL? 1/🧵

Great talk by Marc G. Bellemare at #RLC2026 , ranging from deep RL representations, to stable LLM post-training, to robust statistical measures of performance!