# OffWorld Gym: open-access physical robotics environment for real-world reinforcement learning benchmark and research

arXiv: https://arxiv.org/abs/1910.08639 · HTML: https://mlsanity.com/paper/1910.08639/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2019.

## Built on by (most cited first, 6 of 6)

- [Train Offline, Test Online: A Real Robot Learning Benchmark](https://mlsanity.com/paper/2306.00942/) (2023)
- [Benchmarking Offline Reinforcement Learning on Real-Robot Hardware](https://mlsanity.com/paper/2307.15690/) (2023)
- [Robotic Manipulation Datasets for Offline Compositional Reinforcement Learning](https://mlsanity.com/paper/2307.07091/) (2023)
- [Offline Robot Reinforcement Learning with Uncertainty-Guided Human Expert Sampling](https://mlsanity.com/paper/2212.08232/) (2022)
- [Sim-Env: Decoupling OpenAI Gym Environments from Simulation Models](https://mlsanity.com/paper/2102.09824/) (2021)
- [Markov Cricket: Using Forward and Inverse Reinforcement Learning to Model, Predict And Optimize Batting Performance in One-Day International Cricket](https://mlsanity.com/paper/2103.04349/) (2021)

## Abstract (arXiv)

Success stories of applied machine learning can be traced back to the datasets and environments that were put forward as challenges for the community. The challenge that the community sets as a benchmark is usually the challenge that the community eventually solves. The ultimate challenge of reinforcement learning research is to train real agents to operate in the real environment, but until now there has not been a common real-world RL benchmark. In this work, we present a prototype real-world environment from OffWorld Gym -- a collection of real-world environments for reinforcement learning in robotics with free public remote access. Close integration into existing ecosystem allows the community to start using OffWorld Gym without any prior experience in robotics and takes away the burden of managing a physical robotics system, abstracting it under a familiar API. We introduce a navigation task, where a robot has to reach a visual beacon on an uneven terrain using only the camera input and provide baseline results in both the real environment and the simulated replica. To start training, visit https://gym.offworld.ai