Paul Duckworth

Research Scientist @InstadeepAI

ex-postdoc: @GOALS_oxford @oxfordrobots @OxfordOncology, @ MLRG Oxford
ex-phd: @LeedsUniComp and @LeedsRobotics

[matt @MattVMacfarlane]

Thrilled to see our NeurIPS 2024 paper, Sequential Monte Carlo Policy Optimisation (https://t.co/tnNfRGb7Hn), featured in Kevin's Reinforcement Learning: A Comprehensive Overview, which additionally recognises SMC as a competitive, scalable online planner. A fantastic modern resource on RL! @EdanToledo @DonalByrne2 @pduckw @AlexLaterre

[Paul Duckworth @pduckw]

Excited to be sharing our work on scalable model-based search at NeurIPS tomorrow.
Come chat to us!
Work led by @MattVMacfarlane, @EdanToledo, @DonalByrne2 and @AlexLaterre

[InstaDeep @instadeepai]

Excited to share our latest work on Sequential Monte Carlo Policy Optimisation (SPO)🔥— a scalable, search-based RL algorithm leveraging SMC as a policy improvement operator for both continuous and discrete environments!
📍 Catch us tomorrow at #NeurIPS2024 (poster #94776) from 11 AM–2 PM PST.
Here’s how it works 👇

[Autonomous Robots @AUROblog]

Read latest #openaccess paper: Planning under uncertainty for #saferobotexploration using #Gaussianprocess prediction by @astephens_ @m_budd @pduckw @MauriceFallon @hawesie
🔓https://t.co/GcUTz09GkK
@oxfordrobots @dynamicrobots

[Paul Duckworth @pduckw]

Fantastic achievement by @ClementBonnet16 and the whole Jumanji team!

[Clem Bonnet @ClementBonnet16]

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: https://t.co/IaOXO3MYEd
GitHub: https://t.co/DaSgK8MEtQ

[InstaDeep @instadeepai]

It’s official! 🎉Today InstaDeep becomes a proud member of the BioNTech family. Want to apply your AI skills to make a difference? Join us, we’re hiring!

[Clem Bonnet @ClementBonnet16]

We released a new version of Jumanji (v0.3) with now 18 environments, all with networks and trained checkpoints 🚀
Check out (on arXiv) Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX.

Paper: https://t.co/IaOXO3MYEd
GitHub: https://t.co/DaSgK8MEtQ

[Paul Duckworth @pduckw]

@beenwrekt @SaveToNotion
#Thread

[Paul Duckworth @pduckw]

I'm excited to announce that towards the end of 2022, I started a new role @instadeepai as a Research Scientist. Since then, we've been acquired by @BioNTech_Group. Exciting times ahead!

[Goal-Oriented Autonomous Long-Lived Systems @GOALS_oxford]

If you're at @corl_conf #CoRL2022 and interested in planning under uncertainty for robot missions, make sure to visit @m_budd's poster on Saturday morning!

His work uses GPs as part of a Bayes-optimal framework for planning single missions in partially-known environments.

[Paul Duckworth @pduckw]

@MarcRigter @hawesie Well done Marc! Enjoy your break.

[Paul Duckworth @pduckw]

Friday was my final day at @oxfordrobots and @UniofOxford. I've had a blast. Many thanks to @hawesie and @maosbot for being sensational humans and PIs.

On to the next chapter.

[Paul Duckworth @pduckw]

You can find me at https://t.co/TKPNdMnjw3 also

[Matt Budd @m_budd]

How do you collect valuable data from sensors far under the ocean surface? Our #IROS2022 paper's planner reasons over uncertain localisation 📍, navigation 🧭 and communication 📶 for underwater autonomous vehicles. 1/9
https://t.co/KKUZqdolAx
@GOALS_oxford @hawesie @pduckw

[Goal-Oriented Autonomous Long-Lived Systems @GOALS_oxford]

Without planning it, we were all in the same place at the same time today. Here's a picture of GOALS in 2022!

[Marc Rigter @MarcRigter]

Pleasantly surprised that our paper received runner-up for the best paper award at @ICAPSConference!

The paper is about mitigating risk in MDPs without sacrificing expected performance: https://t.co/xrHYjcz052

Work with @pduckw, Bruno Lacerda, and @hawesie

[Paul Duckworth @pduckw]

@WIRED Well done @drnedatnejadi 👏

[Paul Duckworth @pduckw]

@GEHealthcare Dr Wolfgang Fruehwirt and I researched this question, whilst importantly, taking into account workers' preferences! You can find out more here: https://t.co/L533o8KQka

[Maurice Fallon @MauriceFallon]

The main deadline for DPhil/PhD applications to @oxengsci is in a month (3 Dec 2021). Make sure to have your application in for this date to be eligible for scholarships including for @oxfordrobots.
https://t.co/d4DHkTv7ns

[Paul Duckworth @pduckw]

@arXiv_Daily Inc. @MarcRigter :)