Scaling data-driven robotics with reward sketching and batch reinforcement learning

Citations Over TimeTop 10% of 2020 papers

Abstract

We present a framework for data-driven robotics that makes use of a large dataset of recorded robot experience and scales to several tasks using learned reward functions. We show how to apply this framework to accomplish three different object manipulation tasks on a real robot platform. Given demonstrations of a task together with task-agnostic recorded experience, we use a special form of human annotation as supervision to learn a reward function, which enables us to deal with real-world tasks where the reward signal cannot be acquired directly. Learned rewards are used in combination with a large dataset of experience from different tasks to learn a robot policy offline using batch RL. We show that using our approach it is possible to train agents to perform a variety of challenging manipulation tasks including stacking rigid objects and handling cloth.

Related Papers

• → Optimization of lightweight task offloading strategy for mobile edge computing based on deep reinforcement learning(2019)207 cited
• → Deep reinforcement learning based mobile edge computing for intelligent Internet of Things(2020)124 cited
• → Task offloading method of edge computing in internet of vehicles based on deep reinforcement learning(2022)112 cited
• → Physician-Friendly Machine Learning: A Case Study with Cardiovascular Disease Risk Prediction(2019)71 cited
• → Robotics(2008)8 cited