# Train Offline, Test Online: A Real Robot Learning Benchmark

arXiv: https://arxiv.org/abs/2306.00942 · HTML: https://mlsanity.com/paper/2306.00942/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 1 Jun 2023.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection](https://mlsanity.com/paper/1603.02199/) (2016)
- [RoboNet: Large-Scale Multi-Robot Learning](https://mlsanity.com/paper/1910.11215/) (2019)
- [Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours](https://mlsanity.com/paper/1509.06825/) (2015)
- [RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation](https://mlsanity.com/paper/1811.02790/) (2018)
- [The Unsurprising Effectiveness of Pre-Trained Vision Models for Control](https://mlsanity.com/paper/2203.03580/) (2022)
- [The Surprising Effectiveness of Representation Learning for Visual Imitation](https://mlsanity.com/paper/2112.01511/) (2021)
- [d3rlpy: An Offline Deep Reinforcement Learning Library](https://mlsanity.com/paper/2111.03788/) (2021)
- [Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation](https://mlsanity.com/paper/1810.07121/) (2018)
- [Analysis and Observations from the First Amazon Picking Challenge](https://mlsanity.com/paper/1601.05484/) (2016)
- [Grasping with Chopsticks: Combating Covariate Shift in Model-free Imitation Learning for Fine Manipulation](https://mlsanity.com/paper/2011.06719/) (2020)
- [The Robotarium: A remotely accessible swarm robotics research testbed](https://mlsanity.com/paper/1609.04730/) (2016)
- [OCRTOC: A Cloud-Based Competition and Benchmark for Robotic Grasping and Manipulation](https://mlsanity.com/paper/2104.11446/) (2021)
- [RB2: Robotic Manipulation Benchmarking with a Twist](https://mlsanity.com/paper/2203.08098/) (2022)
- [Hierarchical Neural Dynamic Policies](https://mlsanity.com/paper/2107.05627/) (2021)
- [Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation](https://mlsanity.com/paper/2105.02087/) (2021)
- [Research Challenges and Progress in Robotic Grasping and Manipulation Competitions](https://mlsanity.com/paper/2108.01483/) (2021)
- [OffWorld Gym: open-access physical robotics environment for real-world reinforcement learning benchmark and research](https://mlsanity.com/paper/1910.08639/) (2019)
- [Benchmarking Simulated Robotic Manipulation through a Real World Dataset](https://mlsanity.com/paper/1911.01557/) (2019)

## Built on by (most cited first, 30 of 47)

- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation](https://mlsanity.com/paper/2411.19650/) (2024)
- [UniVLA: Learning to Act Anywhere with Task-centric Latent Actions](https://mlsanity.com/paper/2505.06111/) (2025)
- [iVideoGPT: Interactive VideoGPTs are Scalable World Models](https://mlsanity.com/paper/2405.15223/) (2024)
- [Unified Vision-Language-Action Model](https://mlsanity.com/paper/2506.19850/) (2025)
- [HomeRobot: Open-Vocabulary Mobile Manipulation](https://mlsanity.com/paper/2306.11565/) (2023)
- [Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance](https://mlsanity.com/paper/2410.13816/) (2024)
- [Large Language Models for Robotics: Opportunities, Challenges, and Perspectives](https://mlsanity.com/paper/2401.04334/) (2024)
- [Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications](https://mlsanity.com/paper/2510.07077/) (2025)
- [Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation](https://mlsanity.com/paper/2307.03659/) (2023)
- [RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots](https://mlsanity.com/paper/2603.04356/) (2026)
- [Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics](https://mlsanity.com/paper/2403.19578/) (2024)
- [Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos](https://mlsanity.com/paper/2412.04445/) (2024)
- [Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons](https://mlsanity.com/paper/2603.02115/) (2026)
- [QUAR-VLA: Vision-Language-Action Model for Quadruped Robots](https://mlsanity.com/paper/2312.14457/) (2023)
- [World Action Models: The Next Frontier in Embodied AI](https://mlsanity.com/paper/2605.12090/) (2026)
- [AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World](https://mlsanity.com/paper/2503.24278/) (2025)
- [Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning](https://mlsanity.com/paper/2408.14037/) (2024)
- [DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control](https://mlsanity.com/paper/2409.12192/) (2024)
- [An Unbiased Look at Datasets for Visuo-Motor Pre-Training](https://mlsanity.com/paper/2310.09289/) (2023)
- [Diffusion Transformer Policy](https://mlsanity.com/paper/2410.15959/) (2024)
- [MLA: A Multisensory Language-Action Model for Multimodal Understanding and Forecasting in Robotic Manipulation](https://mlsanity.com/paper/2509.26642/) (2025)
- [XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations](https://mlsanity.com/paper/2511.02776/) (2025)
- [Hearing Touch: Audio-Visual Pretraining for Contact-Rich Manipulation](https://mlsanity.com/paper/2405.08576/) (2024)
- [Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators](https://mlsanity.com/paper/2510.04354/) (2025)
- [Chain of World: World Model Thinking in Latent Motion](https://mlsanity.com/paper/2603.03195/) (2026)
- [LatBot: Distilling Universal Latent Actions for Vision-Language-Action Models](https://mlsanity.com/paper/2511.23034/) (2025)

## Abstract (arXiv)

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 robotic hardware 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.