Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control
Autor: | Andreas Eitel, Max Argus, Wolfram Burgard, Thomas Brox, Lukas Hermann, Artemij Amiranashvili |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2019 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) 05 social sciences Computer Science - Computer Vision and Pattern Recognition 010501 environmental sciences 01 natural sciences Task (project management) Domain (software engineering) Machine Learning (cs.LG) Computer Science - Robotics 0502 economics and business Task analysis Robot Reinforcement learning Artificial intelligence 050207 economics Set (psychology) business Curriculum Robotics (cs.RO) 0105 earth and related environmental sciences Block (data storage) |
Zdroj: | ICRA |
Popis: | We propose Adaptive Curriculum Generation from Demonstrations (ACGD) for reinforcement learning in the presence of sparse rewards. Rather than designing shaped reward functions, ACGD adaptively sets the appropriate task difficulty for the learner by controlling where to sample from the demonstration trajectories and which set of simulation parameters to use. We show that training vision-based control policies in simulation while gradually increasing the difficulty of the task via ACGD improves the policy transfer to the real world. The degree of domain randomization is also gradually increased through the task difficulty. We demonstrate zero-shot transfer for two real-world manipulation tasks: pick-and-stow and block stacking. A video showing the results can be found at https://lmb.informatik.uni-freiburg.de/projects/curriculum/ Accepted at the 2020 IEEE International Conference on Robotics and Automation (ICRA). Project page see https://lmb.informatik.uni-freiburg.de/projects/curriculum/ |
Databáze: | OpenAIRE |
Externí odkaz: |