Improved Learning of Robot Manipulation Tasks via Tactile Intrinsic Motivation
arXiv:2102.11051 · doi:10.1109/LRA.2021.3061308
Abstract
In this paper we address the challenge of exploration in deep reinforcement learning for robotic manipulation tasks. In sparse goal settings, an agent does not receive any positive feedback until randomly achieving the goal, which becomes infeasible for longer control sequences. Inspired by touch-based exploration observed in children, we formulate an intrinsic reward based on the sum of forces between a robot's force sensors and manipulation objects that encourages physical interaction. Furthermore, we introduce contact-prioritized experience replay, a sampling scheme that prioritizes contact rich episodes and transitions. We show that our solution accelerates the exploration and outperforms state-of-the-art methods on three fundamental robot manipulation benchmarks.
arXiv comment8 pages
References in corpus (5)
- Learning agile and dynamic motor skills for legged robots
- Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots
- Demonstration-Guided Deep Reinforcement Learning of Control Policies for Dexterous Human-Robot Interaction
- Learning Functionally Decomposed Hierarchies for Continuous Control Tasks with Path Planning
- How Much Do Unstated Problem Constraints Limit Deep Robotic Reinforcement Learning?