#8 - Meetup in Warsaw (18th June)
Jun
18
Thursday
6PM to 10PM CEST
Register Now »
Main Stage Speakers
Michal Pogoda-Rosikoń
Partner at bards.ai
How do you train AlphaZero-style RL models at 100M steps/sec on one GPU using Jaxpot
View project page
Speaker details and project links
GPU-accelerated reinforcement learning for budget-friendly, high-speed self-play training.
jaxpot
JAX
Flax
Hydra
pgx
