GPU加速シミュレーションによる分散強化学習の高速化
GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning
GPUベースの物理エンジンNVIDIA Flexを用いて強化学習のシミュレーションを高速化し、CPUを大幅に削減しつつ歩行タスクの学習を短時間で実現した。
著者: Jacky Liang, Viktor Makoviychuk, Ankur Handa, Nuttapong Chentanez, Miles Macklin, Dieter Fox
分類: cs.RO
原文アブストラクト
Most Deep Reinforcement Learning (Deep RL) algorithms require a prohibitively large number of training samples for learning complex tasks. Many recent works on speeding up Deep RL have focused on distributed training and simulation. While distributed training is often done on the GPU, simulation is not. In this work, we propose using GPU-accelerated RL simulations as an alternative to CPU ones. Using NVIDIA Flex, a GPU-based physics engine, we show promising speed-ups of learning various continuous-control, locomotion tasks. With one GPU and CPU core, we are able to train the Humanoid running task in less than 20 minutes, using 10-1000x fewer CPU cores than previous works. We also demonstrate the scalability of our simulator to multi-GPU settings to train more challenging locomotion tasks.
