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
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.
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).
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...
...@raphaelboige, @CemlynWaters, Mohamed Mimouni, @ulrichsob, @ruanjohn, Siddarth Singh, @_danielfb, Victor Le, @ArnuPretorius, @AlexLaterre.