Daniel Furelos-Blanco

🚀 Last December we presented ATLAS at NeurIPS @SEAWorkshop. Now thrilled to share at #AAAI2026 @RealAAAI! ⚠️ RL policy generalization across tasks & levels is hard, especially when some tasks aren't realizable. 🗺️ ATLAS tackles this via autocurricula over tasks AND levels 🧵

📍 Saturday Jan 24, #1144 (Hall 4) 🙏 Joint work w/ @pertcj, @FredKel4, @afspies, Alessandra Russo & @MichaelD1729 📄 arxiv.org/abs/2511.12706 💻 github.com/spike-imperial… Come chat with us!

🗺️ ATLAS creates autocurricula over BOTH tasks (reward machines) AND levels (Minigrid), enabling it to 🔹learn good policies even when solvable tasks are rarely sampled, 🔹perform mutations over tasks and levels jointly to bootstrap complex curricula from simple pairs.

🚀 Last December we presented ATLAS at NeurIPS @SEAWorkshop. Now thrilled to share at #AAAI2026 @RealAAAI! ⚠️ RL policy generalization across tasks & levels is hard, especially when some tasks aren't realizable. 🗺️ ATLAS tackles this via autocurricula over tasks AND levels 🧵

Wouldn't it be nice if there was a way to organize attention heads in LLMs by the patterns they produce? Poster @ NeurIPS mechint workshop, more in 🧵

📍 Poster session: 12:00–13:10 Joint work with @pertcj, @FredKel4, @afspies, Alessandra Russo & @MichaelD1729 📄 arxiv.org/abs/2511.12706 Come chat with us!

ATLAS creates autocurricula over BOTH tasks (reward machines) AND levels (Minigrid), enabling it to 🔹learn good policies even when solvable tasks are rarely sampled, 🔹perform mutations over levels and tasks jointly to bootstrap complex curricula from simple task-level pairs.

We build upon existing work: 🔹UED → Generate auto-curricula, but only over levels. Task is fixed. 🔹Formal language conditioning (temporal logic, state machines) → generalize over tasks & levels, but just sample randomly - no autocurriculum. We propose ATLAS to extend these.

🚀 Thrilled to be presenting ATLAS at the @SEAWorkshop at #NeurIPS2025 this Sunday! Training RL agents to generalize across diverse levels and tasks is hard, especially when some tasks are not always realizable. ATLAS tackles this by creating curricula over tasks AND levels 🧵

It was a pleasure to have @dabelcs present this work last October at @SPIKE_ICL! 📽️ The recording of the talk is now available: youtube.com/watch?v=XWxP_q… Don't miss their poster at #NeurIPS2025 🚀

@BalsellsRodas @yixinwang_ @liyzhen2 Very well deserved, Carles! Congrats! 🎉

🎉Happy to share that our paper “On the Identifiability of Switching Dynamical Systems” has been accepted to ICML! Preprint: arxiv.org/abs/2305.15925 @yixinwang_ @liyzhen2

Excited to announce Jumanji v1.0, now featuring 22 fast, flexible, and scalable environments! Fully written in JAX, Jumanji offers on-device fully-jitted simulations and training. Jumanji got published at ICLR 2024! Paper: arxiv.org/abs/2306.09884 GitHub: github.com/instadeepai/ju…

Excited to announce 2 papers on performance-driven diversity for RL and combinatorial optimization to be presented at Neurips today 📢 Some problems are simply too difficult to be solved with a single shot. But if you have several shots, how to make the most of them? 🧵1/7

@y0b1byte "Toxicity" by System of a Down? :D

From the inside of the headphones, I definitely sounded much better xD Guess the song

@UofTCompSci @SheilaMcIlraith Congratulations Alberto and Rodrigo! Very well deserved :)

Congratulations to alumni Alberto Camacho and Rodrigo Toro Icarte, both supervised by Professor @SheilaMcIlraith, who were recognized for their doctoral theses at #ICAPS2023. uoft.me/9vX

Oral: Tue 25, 17:30 - Oral A6 Reinforcement Learning 2 - Ballroom C Poster: Thu 27, 13:30 - Exhibit Hall 1 #420 Paper: proceedings.mlr.press/v202/furelos-b… Code: github.com/ertsiger/hrm-l…

Aloha! 🌴 This week I'm at #ICML2023 presenting "Hierarchies of Reward Machines". We increase the abstraction power of reward machines (RMs) by enabling them to call each other, composing a hierarchy of RMs (HRM). We describe methods for both exploiting and learning HRMs.

1/ We are delighted to share our recent work, Poppy 🌺 “Population-Based Reinforcement Learning for Combinatorial Optimization”, which achieves SOTA RL performance on canonical NP-hard combinatorial problems 🚀. 📚 Paper: arxiv.org/abs/2210.03475 📖 Blog: bit.ly/3stDenZ

New Article: "Induction and Exploitation of Subgoal Automata for Reinforcement Learning" by Furelos-Blanco, Law, Jonsson, Broda and Russo bit.ly/30wuyz1