Train Offline, Test Online: A Real Robot Learning Benchmark

Gaoyue Zhou, Victoria Dean, Mohan Kumar Srirama, Aravind Rajeswaran, Jyothish Pari, Kyle Beltran Hatch, Aryan Jain, Tianhe Yu, Pieter Abbeel, Lerrel Pinto, Chelsea Finn, Abhinav Gupta

Keywords: benchmarking, robot learning, offline reinforcement learning, datasets, machine learning for robot control

TL;DR: We introduce a new benchmark for tabletop manipulation: Train Offline, Test Online (TOTO) and showed performance of state-of-the-art models on two tasks

Abstract: Three challenges limit the progress of robot learning research: robots are expensive (few labs can participate), everyone uses different robots (findings do not generalize across labs), and we lack internet-scale robotics data. We take on these challenges via a new benchmark: Train Offline, Test Online (TOTO). TOTO provides remote users with access to shared robots for evaluating methods on common tasks and an open-source dataset of these tasks for offline training. Its manipulation task suite requires challenging generalization to unseen objects, positions, and lighting. We present initial results on TOTO comparing five pretrained visual representations and four offline policy learning baselines, remotely contributed by five institutions. The real promise of TOTO, however, lies in the future: we release the benchmark for additional submissions from any user, enabling easy, direct comparison to several methods without the need to obtain hardware or collect data.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/train-offline-test-online-a-real-robot/code)