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

Abstract

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

References in corpus (30)

• Continuous control with deep reinforcement learning
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Trust Region Policy Optimization
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
• Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
• VIME: Variational Information Maximizing Exploration
• Rainbow: Combining Improvements in Deep Reinforcement Learning
• Learning Continuous Control Policies by Stochastic Value Gradients
• Continuous Deep Q-Learning with Model-based Acceleration
• CARLA: An Open Urban Driving Simulator
• One-Shot Visual Imitation Learning via Meta-Learning
• Learning Dexterous In-Hand Manipulation
• Challenges of Real-World Reinforcement Learning
• Memory-based control with recurrent neural networks
• Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control
• Go-Explore: a New Approach for Hard-Exploration Problems
• Unsupervised Predictive Memory in a Goal-Directed Agent
• Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search
• Model-Based Reinforcement Learning via Meta-Policy Optimization
• PyRep: Bringing V-REP to Deep Robot Learning
• Extending the OpenAI Gym for robotics: a toolkit for reinforcement learning using ROS and Gazebo
• PyRobot: An Open-source Robotics Framework for Research and Benchmarking
• RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation
• TarMAC: Targeted Multi-Agent Communication
• REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning
• Learning latent state representation for speeding up exploration
• Provably Efficient Imitation Learning from Observation Alone
• Self-Supervised Exploration via Disagreement
• ORRB -- OpenAI Remote Rendering Backend

Cited by in corpus (3)

• Markov Cricket: Using Forward and Inverse Reinforcement Learning to Model, Predict And Optimize Batting Performance in One-Day International Cricket
• Sim-Env: Decoupling OpenAI Gym Environments from Simulation Models
• Deep Reinforcement Learning for Tactile Robotics: Learning to Type on a Braille Keyboard