BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGym

07/09/2021
by   Rika Antonova, et al.
0

BayesSim is a statistical technique for domain randomization in reinforcement learning based on likelihood-free inference of simulation parameters. This paper outlines BayesSimIG: a library that provides an implementation of BayesSim integrated with the recently released NVIDIA IsaacGym. This combination allows large-scale parameter inference with end-to-end GPU acceleration. Both inference and simulation get GPU speedup, with support for running more than 10K parallel simulation environments for complex robotics tasks that can have more than 100 simulation parameters to estimate. BayesSimIG provides an integration with TensorBoard to easily visualize slices of high-dimensional posteriors. The library is built in a modular way to support research experiments with novel ways to collect and process the trajectories from the parallel IsaacGym environments.

READ FULL TEXT
research
11/22/2019

Titan: A Parallel Asynchronous Library for Multi-Agent and Soft-Body Robotics using NVIDIA CUDA

While most robotics simulation libraries are built for low-dimensional a...
research
06/04/2019

BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators

We introduce BayesSim, a framework for robotics simulations allowing a f...
research
05/17/2022

DeepSim: A Reinforcement Learning Environment Build Toolkit for ROS and Gazebo

We propose DeepSim, a reinforcement learning environment build toolkit f...
research
06/29/2022

Online vs. Offline Adaptive Domain Randomization Benchmark

Physics simulators have shown great promise for conveniently learning re...
research
10/17/2022

Merlin HugeCTR: GPU-accelerated Recommender System Training and Inference

In this talk, we introduce Merlin HugeCTR. Merlin HugeCTR is an open sou...
research
03/12/2021

Large Batch Simulation for Deep Reinforcement Learning

We accelerate deep reinforcement learning-based training in visually com...
research
06/26/2019

ORRB – OpenAI Remote Rendering Backend

We present the OpenAI Remote Rendering Backend (ORRB), a system that all...

Please sign up or login with your details

Forgot password? Click here to reset