π Rejax & Meta-Synth-Envs Are Out π
Date:
Super excited to share that our work on fast hardware-accelerated Deep RL algorithms π and Synthetic Environments π is finally out!
We implement various DRL algorithms (PPO, DQN, DDPG, SAC, etc.) in pure JAX, which are all nicely packaged into rejax. Furthermore, we leverage meta-evolution (with evosax) to discover synthetic MDPs (more specifically contextual bandits!!!) for fast training of agents that perform well in their real counterpart environments.
This work was led by my fantastic MSc student Jarek Liesen who will soon join FLAIR at the University of Oxford for his PhD. I am extremely grateful for the opportunity to work with such brilliant students!
π€ Rejax: here. π Synth-Gymnax: here. π Paper: here. π₯ Twitter: here.