Sven MikainDistributed Computing with RayAttention Nets and More with RLlib’s Trajectory View APIIn this blog post, we’re announcing two new features now stable in RLlib: Support for Attention networks as custom models, and the…Apr 21, 2021Apr 21, 2021
Sven MikainDistributed Computing with RayReinforcement Learning with RLlib in the Unity Game EngineA Unity3D game world: Learning complex behaviors in arbitrary virtual worlds — from scratch and without much supervision — will become the…Jan 26, 20214Jan 26, 20214
Sven MikainDistributed Computing with RayLessons from implementing 12 Deep RL Algorithms in TF and PyTorchIn this blog post, I discuss my experience porting 12 different deep RL (reinforcement learning) algos for RLlib from TensorFlow to…Sep 23, 20203Sep 23, 20203