~~RL project progress~~ wrote a FAST (88M steps/s) parallelized env in jax from scratch. here's its renderer:

i used LLMs to write the renderer btw. im learning RL not openGL the core jax env under the hood is what matters. its steps/s == how fast I can train a model on it SoA and jax.jit do the heavy lifting here. future optimizations: replace loops with scans, run on a cloud gpu

very cool who is the agent and whats its learning objective in this sim?

right now there is no agent, just the parallelizable env and renderer the agent will be a planet whose objective is a bit complex. but essentially its goal is to guarantee survival

looks so coooool !!

very cool

88 million steps/s?? holy shit

@yacineMTB Impressive work! Building a FAST parallelized env from scratch is no small feat. What's next on your agenda? 🚀 #Innovation