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: arxiv.org/abs/2306.09884 GitHub: github.com/instadeepai/juman…

Mar 19, 2024 · 12:13 PM UTC

1
28
3
125
31,225
Jumanji implements computational, often NP-hard, problems as jittable simulations for AI systems to train on and learn to master. You can think of a not-so-distant future where simulations become ubiquitous and allow safe AI training on specific (distribution of) problems.
1
4
516
If you haven't yet, please check out the amazing works from the JAX community. E.g. environments: Brax (@OlivierBachem), Gymnax (@RobertTLange), JaxMARL (@alexrutherford0), Craftax (@mitrma), Pgx (@sotetsuk). And algorithms: PureJaxRL (@_chris_lu_), Stoix/Flashbax (@EdanToledo).
1
3
11
1,020
Jumanji has been built with the amazing @instadeepai team, including Daniel Luo, @DonalByrne2, @ShikhaSurana01, @S_Abramowitz96, @pduckw, Vincent Coyette, @SilkyDogfish, @pour_qua, Tristan Kalloniatis, @MahjoubOmayma, Matthew Macfarlane, @DriesSmit1, @NGrinsztajn...
1
3
447