Jonathan Shock
@jonsadventures
Associate Professor at the University of Cape Town
ID:20323216
http://www.shocklab.net 07-02-2009 18:05:03
99 Tweets
227 Followers
218 Following
I am extremely grateful to my co-organisers UT3 Paul Sabatier IFAS-Research, and to the speakers and the delegates from the France in South Africa National Research Foundation of South Africa Wits University and CNRS in Southern Africa for their contribution and support to the #BrAInEvolution conference. We'll share more soon!
'Sophisticated Learning' (SL) is a new extension of 'sophisticated active inference' (SI) planning algorithms. SL combines SI with elements of Bayesian RL and outperforms both on specific planning problems.
arxiv.org/abs/2308.08029
Developed by Rowan Hodson. Feedback welcome!
I gave a couple of talks recently for the general public on an introduction to Artificial Intelligence, to the Oxford University IT Learning Centre, thanks to IT Learning Centre, University of Oxford Emma Procter-Legg #FE #HE . Here's a recording of the first:
youtube.com/watch?v=vGgxnv…
OUT NOW: pre-print non-final PDF of our book 'Multi-Agent Reinforcement Learning: Foundations and Modern Approaches' released on official page marl-book.com. The authors (I, Filippos Christianos, Lukas Schäfer) will be at @aamas2023 & ICRA2024 in London. The MIT Press @mitpress.bsky.social
I would like to thank my supervisors Jonathan Shock and Arnu Pretorius for their invaluable guidance on this project.
This work was made possible by the support from InstaDeep and UCT Research 🇿🇦
[1/3] Excited to share that our paper titled 'Selective Reincarnation in MARL' was chosen for an oral presentation at the Reincarnating RL workshop at ICLR 2024 🇷🇼 Congratulations to my co-authors from InstaDeep, Callum Rhys Tilbury, Kale-ab Tessera and Arnu Pretorius 🇿🇦