From Scratch to Sketch: Deep Decoupled Hierarchical Reinforcement Learning for Robotic Sketching Agent

Abstract

We present an automated learning framework for a robotic sketching agent that is capable of learning stroke-based rendering and motor control simultaneously. We formulate the robotic sketching problem as a deep decoupled hierarchical reinforcement learning; two policies for stroke-based rendering and motor control are learned independently to achieve sub-tasks for drawing, and form a hierarchy when cooperating for real-world drawing. Without hand-crafted features, drawing sequences or trajectories, and inverse kinematics, the proposed method trains the robotic sketching agent from scratch. We performed experiments with a 6-DoF robot arm with 2F gripper to sketch doodles. Our experimental results show that the two policies successfully learned the sub-tasks and collaborated to sketch the target images. Also, the robustness and flexibility were examined by varying drawing tools and surfaces.

arXiv commentAccepted to ICRA 2022

References in corpus (9)

• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Spectral Normalization for Generative Adversarial Networks
• A Neural Representation of Sketch Drawings
• Visual Reinforcement Learning with Imagined Goals
• Synthesizing Programs for Images using Reinforced Adversarial Learning
• Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?
• Unsupervised Control Through Non-Parametric Discriminative Rewards
• Many-Goals Reinforcement Learning
• Unsupervised Doodling and Painting with Improved SPIRAL