
Research Engineer @EpicGames | Formerly PhD @ImperialCollege
Joined January 2016
- Tweets22
- Following401
- Followers92
- Likes709
🗺️ 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.
1
1
118
We build upon prior work:
🔹UED → Generate autocurricula, 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.
1
1
79
🚀 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 🧵
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.
1
2
122
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.
1
2
152
🚀 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_qrj…
Don't miss their poster at #NeurIPS2025 🚀
Thrilled to share our new #NeurIPS2025 paper done at @GoogleDeepMind, Plasticity as the Mirror of Empowerment
We prove every agent faces a trade-off between its capacity to adapt (plasticity) and its capacity to steer (empowerment)
Paper: david-abel.github.io/plastic…
🧵🧵🧵👇
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.






