GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning

10/12/2018
by   Jacky Liang, et al.
0

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.

READ FULL TEXT

page 2

page 11

research
12/08/2020

The Architectural Implications of Distributed Reinforcement Learning on CPU-GPU Systems

With deep reinforcement learning (RL) methods achieving results that exc...
research
08/24/2021

Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning

Isaac Gym offers a high performance learning platform to train policies ...
research
10/16/2019

Hyper: Distributed Cloud Processing for Large-Scale Deep Learning Tasks

Training and deploying deep learning models in real-world applications r...
research
04/14/2022

Accelerated Policy Learning with Parallel Differentiable Simulation

Deep reinforcement learning can generate complex control policies, but r...
research
07/19/2019

GPU-Accelerated Atari Emulation for Reinforcement Learning

We designed and implemented a CUDA port of the Atari Learning Environmen...
research
07/15/2022

Optimizing Data Collection in Deep Reinforcement Learning

Reinforcement learning (RL) workloads take a notoriously long time to tr...
research
02/08/2021

RL-Scope: Cross-Stack Profiling for Deep Reinforcement Learning Workloads

Deep reinforcement learning (RL) has made groundbreaking advancements in...

Please sign up or login with your details

Forgot password? Click here to reset