Foerster Lab for AI Research (now part of BOLD)

Follow @bold_lab_ai for updates!

[Foerster Lab for AI Research (now part of BOLD) @FLAIR_Ox]

🚀 Absolutely delighted to announce BOLD, a new frontier lab for open-ended learning and discovery, based in the UK. Moving forward, we will be part of BOLD - so follow @bold_lab_ai for information about foundational frontier AI research, opportunities, and BOLD events!

[British Open-ended Learning and Discovery Lab @bold_lab_ai]

Hello world :)
We are BOLD — the British Open-ended Learning and Discovery Lab!

BOLD is a new academic research lab fully focussed on paradigm breaking discoveries in fundamental AI. We work towards more efficient & open AI that is built around human needs and capabilities.

To pursue these breakthroughs, we pioneer new modes of collaboration in academia that are more focussed, resourced, agile, and collaborative. Rather than fragmenting resources, today we are sunsetting 5 of the UKs leading AI labs to join forces under our joined scientific vision.

Our vision is centered around three pillars:
⚡ Beyond backpropagation – questioning the foundations of the field.
🤝 Human-centric learning & discovery – treating humans as core to our algorithms
🤖 Embodied learning – fast learning and adapting methods that deal with the messy real world

BOLD is backed by @UKRI_News and @EPSRC with £30M – and this is just the beginning. We are urgently looking for partners and sponsors to 10x this.

👉 https://t.co/eFVFW31mqz

👉 https://t.co/Eoad4G18KL

@j_foerst, @CULLYAntoine, @tonizza82, @shimon8282, @tonizza82, Ani Calinescu & @_rockt

[Alistair Letcher @_aletcher]

Model-free agents learn to maximise reward without modelling the environment. Right?

In recent work, we challenge this narrative by proving that agents, trained on a sufficiently rich set of goals, encode a unique and accurate world model in their value functions.
1/

[Michael Matthews @mitrma]

⛳ Introducing purejaxgcrl: goal-conditioned reinforcement learning in end-to-end JAX for discrete action environments!

Train generalist, goal-conditioned agents in minutes on a single GPU.
1/

[Uljad @uljadb99]

Now an @ALifeConf 2026 Oral! Grateful to my amazing collaborators @ZelaArber @j_foerst and @FrankRHutter

[Clarisse Wibault @ClarisseWibault]

Mean Field Games provide a framework for modelling large populations.
ICML26 Spotlight: Introducing Recurrent Structural Policy Gradient for partially observable MFGs with common noise, benefitting from faster convergence than model-free RL, but remaining tractable, unlike DP.

[Michael Matthews @mitrma]

Hindsight Experience Replay has become the ubiquitous method for goal-conditioned reinforcement learning, but leaves open the question of which goal to relabel with.

In this work, accepted at ICML, we propose instead simply Learning Everything All at Once (LEO).
1/

[Clarisse Wibault @ClarisseWibault]

CV has CNNs, NLP has transformers - what inductive bias does RL have? How can policies generalise to regions of the dataset suffering from poor transitions?

We motivate hierarchy by enabling distinct state-representations at different levels of the hierarchy @FLAIR_Ox @j_foerst

[Alex Goldie @ ICML 2026 🇰🇷 @AlexDGoldie]

Really excited to be giving a talk at the first AIDDA event!

[Bidipta Sarkar @bidiptas13]

Ton of EGGROLL updates to give since this post, but basically

- We have a vLLM implementation
- New experiments (world model ft, quantised training)
- New theory (high-dim convergence at low rank)
- Accepted to ICML; see y'all in Seoul

[Alex Goldie @ ICML 2026 🇰🇷 @AlexDGoldie]

So happy to announce that DiscoGen has been accepted to ICML! See you all in Seoul!

I really strongly believe that large scale, open-ended (meta-meta-)optimisation enabled by PCG is a game-changer for automated algorithm discovery and research. Let me know if you want to chat!

[Uljad @uljadb99]

Natural evolution's open-endedness leads to beautiful, complex emergent structures and self-organizing behavior 🌱✨. Replicating this in silico is famously hard 💻. Our paper points to a promising direction by evolving populations of competing neural cellular automata with lifelike behavior 🧬🤖 #Isambard

⚠️⚠️flashing lights, rapid cuts, or strobe effects in this thread! 🚨🚨

1/n

[J Rosser ✈️ ICML @jrosseruk]

Introducing ✨Infusion✨, our *new paper* made possible by the UK AISI Challenge Fund and Sovereign AI!

1/8🧵 TL;DR

Influence functions are commonly used to attribute model behavior to its training data. In this paper we explored the reverse: whether it's possible to use influence functions to craft training data that induces model behavior?

Huge thank you to my amazing collaborators for making this possible
@LauraRuis @_robertkirk @egrefen @j_foerst and of course
@AISecurityInst and @UKSovereignAI!

[Michael Beukman @mcbeukman]

1/ As compute continues to grow and simulators continue to improve, it is becoming feasible to train RL agents for billions or trillions of timesteps. However, this is only useful if agents can continue learning over such long training horizons, which is far from given 👇

[Alex Goldie @ ICML 2026 🇰🇷 @AlexDGoldie]

1/ 🪩 Automating the discovery of new algorithms could unlock significant breakthroughs in ML research. But optimising agents for this research has been limited by too few tasks to learn from!

Introducing DiscoGen, a procedural generator of algorithm discovery tasks 🧵

[Foerster Lab for AI Research (now part of BOLD) @FLAIR_Ox]

How can MARL be used to train driving policies in new cities without needing any human demonstration?

Check out our new paper to find out!

[Zilin Wang @zilinwang4ai]

1/ 🚗 🌏 What if an autonomous vehicle could move to a new city without collecting a single human demonstration in that city?

I am so excited to introduce our new work: Learning to Drive in New Cities Without Human Demonstrations.

[Foerster Lab for AI Research (now part of BOLD) @FLAIR_Ox]

🚨🪩 DiscoBench is a new system for evaluating automated algorithm discovery systems from FLAIR! Check it out and give it a go 🚀🚀

[Alex Goldie @ ICML 2026 🇰🇷 @AlexDGoldie]

🪩 So excited to reveal DiscoBench: An Open-Ended Benchmark for Algorithm Discovery! 🪩

It addresses the key issues of current evals with its broad task coverage, modular file system, meta-train/meta-test split and emphasis on open-ended tasks! 🧵

[Foerster Lab for AI Research (now part of BOLD) @FLAIR_Ox]

🥚EGGROLL is a new method for evolution at the ⚡️hyperscale⚡️!

✅ Population size > 100,000 on one GPU
✅Training LLMs in Int8
✅100x training throughput

🤯Check out this work below!

[Bidipta Sarkar @bidiptas13]

Introducing 🥚EGGROLL 🥚(Evolution Guided General Optimization via Low-rank Learning)! 🚀 Scaling backprop-free Evolution Strategies (ES) for billion-parameter models at large population sizes

⚡100x Training Throughput
🎯Fast Convergence
🔢Pure Int8 Pretraining of RNN LLMs

[Jakob Foerster @j_foerst]

My Oxford lab (@FLAIR_Ox ) is hiring Phd students! If you are thinking of doing a Phd in blue-sky and -sort of crazy ambitious- ML and have a technically strong background and love to work with others, please consider all options for joining us:
1) Direct entry - deadline is the 1st of Dec AOE (https://t.co/lgLZdUXJpA)
2) AIMS CDT (https://t.co/L0dDvIGiAP) deadline on 27th of Jan 2026 AOE
3) EIT CDT (https://t.co/8xfPKHM4AJ) deadline on the 7th of Jan 2026 AOE

Student funding is a real constraint / concern in the UK (especially for overseas students) and by applying for these three programs you can maximize your chances of ending up in a very very special place.

[Foerster Lab for AI Research (now part of BOLD) @FLAIR_Ox]

An Oral at NeurIPS, co-led by 3 Flair PhDs 🍾

We’re building one of the most talent-dense and collaborative labs in the world… If you’re interested, reach out!

[Matthew Jackson @JacksonMattT]

Unifloral has been accepted as an Oral at NeurIPS 2025!

Immensely grateful to my @FLAIR_Ox co-authors @uljadb99 and @JarekLiesen for pouring months of effort into this project.

There’s a ton of low-hanging fruit in offline RL… If you’re looking for a project, check it out!

[nathan monette @nathanrmonette]

As a former FLAIR intern, I can happily say that this is an amazing opportunity.

I met fantastic researchers and was able to publish my own paper at @RL_Conference this year.

Please apply if eligible and interested, you won’t regret it!