@az_prd

PhD student at @UniOfOxford. RL and world models. Member of @bold_lab_ai (formerly @whi_rl). RSI @Meta

 Oxford, England
scholar.google.com/citations?hl=en&user=x17I0JcAAAAJ
Joined May 2011
  • Tweets40
  • Following262
  • Followers110
Alex Zakharov retweeted
Jakob Foerster
@j_foerstAug 21
TL;DR: This is one of the most important and exciting opportunities in AI on the planet - please read on. The British Open-ended Learning & Discovery Lab is creating the perfect place for paradigm breaking AI research in the name of open-source and open-science. We have agency, we funding, we have unprecedented amounts of compute*, but WE NEED YOU! ..and we have created the dream job for you: The BOLD Fellow. This job combines a fast-moving, high agency, collaborative environment with full academic freedom and a salary that pays the bills. Apply by noon UK time on the 15th of September for this once in a lifetime opportunity to shape the history of our field and of our planet: my.corehr.com/pls/uoxrecruit… *by academic standards
20
96
23
445
122,228
Alex Zakharov retweeted
Jakob Foerster
@j_foerstJul 14
BOLD is hiring 🚀 Right now we are looking for two brilliant individuals to help us build the machine that invents the future. If you are up for a challenge and thrive in a fast moving, collaborative, mission driven environment, this is for you..! Links and more info👇
3
20
7
105
33,581
Over this week, we'll be posting about papers from BOLD on show at the upcoming #ICML2026. Up first: LEO, led by @mitrma! Typical approaches in goal-conditioned RL select a single goal that is completed later in the episode. This paper instead asks a simple question: what if *every* goal is used for labelling (and how could we do that efficiently)? Check it out: arxiv.org/pdf/2605.23551
8
1
36
3,628
The world doesn't wait for you to decide on an optimal action... but that's how we treat most RL research! Real-time RL learns how (and when) to plan - all while the environment is progressing in real-time. 👇 Check out our new paper!
Aneesh Muppidi
@aneeshersJun 30
Introducing Real-time RL. In the real world, time isn't free. The environment keeps "moving" even when you're computing your next action. We show how RL agents can learn to adaptively think in real-time games. 1/🧵
7
30
3,909
🛌💭Our next ICML paper is Dreaming in Code, led by @k_mitsides. In this work, LLMs are used as architects of experience: writing worlds in code that scaffold an RL agent towards long-horizon skills it could not discover alone! Check out the project page at: konstantinosmitsides.github.… And the paper: arxiv.org/pdf/2602.08194

Dreaming in Code for Curriculum Learning in Open-Ended Worlds

Foundation models dream executable environments to teach RL agents long-horizon skills. ICML 2026.

konstantinosmitsides.github.io
14
40
3,331
🔦 Another #ICML2026 paper from BOLD, and this time it's a SPOTLIGHT led by @ClarisseWibault. In this work, we introduce Recurrent Structural Policy Gradient for Partially Observable Mean-field Games with Common Noise. Our algorithm learns more realistic history-dependent behaviour, while also leveraging known structure to benefit from faster convergence than model-free RL methods! Check out the project page at: clarisse-wibault.github.io/r…, which includes links to our Mean-Field Game library, as well as a Google Colab example implementation! And the paper at: arxiv.org/pdf/2602.20141
6
1
24
3,159
🪩 Next #ICML2026 paper: DiscoGen, led by @AlexDGoldie. DiscoGen is a procedural generator of algorithm discovery problems for AI research agents, supporting the creation of over 100 billion diverse tasks! Tasks vary across many axes, such as their field of machine learning or datasets they use. They can even support different evaluations, such as the time an algorithm takes to train (speedrunning ⚡️), its energy usage (efficiency 🌱) or its performance 💪! Check out the paper at: arxiv.org/pdf/2603.17863 Give the code a look: github.com/AlexGoldie/discog… Or install the DiscoGen package for your research: pip install discogen
13
46
2,753
Couldn’t be happier to be a part of BOLD! Amazing people, amazing times ahead
British Open-ended Learning and Discovery Lab
@bold_lab_aiJun 23
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. 👉 ox.ac.uk/news/2026-06-22-oxf… 👉 bold-lab.ai @j_foerst, @CULLYAntoine, @tonizza82, @shimon8282, @tonizza82, Ani Calinescu & @_rockt
10
340
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. 👉 ox.ac.uk/news/2026-06-22-oxf… 👉 bold-lab.ai @j_foerst, @CULLYAntoine, @tonizza82, @shimon8282, @tonizza82, Ani Calinescu & @_rockt
22
51
27
240
102,426
Alex Zakharov retweeted
Alex Goldie@AlexDGoldieMar 25
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 🧵
4
44
9
196
65,426
Alex Zakharov retweeted
Hamza Adnan@_hamzaadnan_Feb 10
My first paper with @JacksonMattT and @az_prd is out on arXiv! Introducing MaskLAM: a simple, architecture-free tweak that makes Latent Action Models (LAMs) focus on agents ONLY: 4× higher returns, 3× better latent actions, and a step towards learning from unlabelled videos! ⬇️
1
1
1
92
Come join us at Friedman 102!
This Post is from an account that no longer exists. Learn more
1
Excited to announce our #RLDM2022 workshop "Temporal Representation in RL" on 11 June @BrownUniversity ⚡️ We have an amazing lineup of speakers discussing time in biological & artificial brains incl. @RichardSSutton, Marc Howard and @criticalneuro! See: trirl.cc/

Temporal Representation in Reinforcement Learning (TRiRL)

Reinforcement Learning and Decision Making Workshop

trirl.cc
2
7
29
Come check out our new paper at ICLR2022! 🚨 We introduce a hierarchical generative model for videos, which continuously controls its hierarchical depth for processing.
Zafeirios Fountas
@zfountas27 Apr 2022
⚡️Our new work with @az_prd titled "Variational predictive routing with nested subjective timescales" (#VPR) is presented at #ICLR2022 tomorrow 28 Apr at 10:30 am — 12:30pm BST. iclr.cc/virtual/2022/poster/… VPR is an event-based hierarchical generative model for videos… 🧵👇
5
Alex Zakharov retweeted
jared tumiel@jnearestn16 Oct 2020
How do you learn about something exciting, new, and interdisciplinary? A syllabus of course! Today I'm releasing my own version of a syllabus to go deeper on the Free Energy Principle and Active Inference jaredtumiel.github.io/blog/2…

Spinning Up in Active Inference and the Free Energy Principle

A Syllabus for the Curious

jaredtumiel.github.io
5
31
6
82
Alex Zakharov retweeted
I.Share@IAMNERDIShare7 Oct 2020
I didn't go to work because a cat fell on my head and then a dog with shoes tried to do me justice.
5,856
275,359
27,461
1,020,499
Alex Zakharov retweeted
Amir Alansary@amiralansary8 Oct 2020
Join us this afternoon to check our @Grail2020 @MICCAI2020 work age prediction using @DevelopingHCP brain surfaces presented by my student @az_prd Thanks @DanielRueckert @schuhschuh & all coauthors from @BioMedIAICL Paper arxiv.org/abs/2008.06098 Code github.com/andwang1/BrainSur…
1
3
13
Alex Zakharov retweeted
Zafeirios Fountas
@zfountas6 Oct 2020
2 things to share! 1) A few days ago, our paper on Deep active inference with MC methods got accepted @ #NeurIPS2020🥳 2) We released this exciting work that connects DAI with episodic memory & subjective time resulting in the following very cool features for model-based agents:
Matt McGill@MattMcGill_6 Oct 2020
Preprint Time! Episodic Memory for Learning Subjective-Timescale Models arxiv.org/pdf/2010.01430.pdf Basic idea: Store only "interesting" memories and learn dynamics between them. Plan actions to get to interesting states skipping the boring stuff. This has many cool properties..1/6
2
15
Alex Zakharov retweeted
Matt McGill@MattMcGill_6 Oct 2020
Preprint Time! Episodic Memory for Learning Subjective-Timescale Models arxiv.org/pdf/2010.01430.pdf Basic idea: Store only "interesting" memories and learn dynamics between them. Plan actions to get to interesting states skipping the boring stuff. This has many cool properties..1/6
3
15
5
84
Load more