Massive effort from amazing collaborators @allardmaxime079@MFlageat and @CULLYAntoine. Super thankful for the opportunity and privilege to play a part in this work!
3/3
Super happy to share that our work on robot adaptation is now out in @NatureComms!
Imagine a robot being paralysed in some areas from unknown failures like a faulty or damaged wheel or motor, operating and driving such a vehicle is near impossible.
๐งต1/3
๐คThrilled to share that robotics work from my PhD is out in @NatureComms ๐
"Getting robots back on track by reconstituting control in unexpected situations with online learning"
With @MFlageat , @bryanlimwt , @CULLYAntoine@imperialcollege
๐งตbelow
Turning right becomes moving straight, going straight means turning left. This work is our attempt at addressing this through rapid online learning. Regaining control of the robot again and operating and driving it as if nothing was wrong felt magical!
2/3
๐กโ๏ธ Ideas and inventions are rarely generated and created in isolation ๐๏ธ
We explore using few/many-shot prompting of language models with quality-diverse examples provided from QD algorithms for solution generation for QD problems!
Work done with @MFlageat@CULLYAntoine
๐กโ๏ธ Ideas and inventions are rarely generated and created in isolation ๐๏ธ
We explore using few/many-shot prompting of language models with quality-diverse examples provided from QD algorithms for solution generation for QD problems!
Work done with @MFlageat@CULLYAntoine
Compared to other QD algorithms which use a few solutions from the archive for the next offspring (i.e. parents for a mutation/crossover or the init of an ES mean dist.), In-context QD makes greater use of the quality-diverse solutions in the archive for solution generation
Itโll be right after the Euro finals โฝ so come on over after all the excitement/joy/disappointment. See you there! Room 112 if youโre in-person in Melbourne!
Excited to be presenting this yearโs edition of Evolutionary Reinforcement Learning (EvoRL) @GeccoConf ๐ฆ๐ฆพ with @MFlageat@CULLYAntoine, which will be a tutorial instead of a workshop!
๐งต
We believe there are still many things that all the different ideas and sub-fields of evolution can bring to RL and vice-verca, so the goal of this tutorial is to really encourage that ๐๐๐
Very happy to share that I passed my PhD viva yesterday! Extremely grateful to @CULLYAntoine who has been a great advisor and mentor throughout this journey. Thank you for giving me this opportunity of a lifetime!