Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets

Abstract

Imitation learning has traditionally been applied to learn a single task from demonstrations thereof. The requirement of structured and isolated demonstrations limits the scalability of imitation learning approaches as they are difficult to apply to real-world scenarios, where robots have to be able to execute a multitude of tasks. In this paper, we propose a multi-modal imitation learning framework that is able to segment and imitate skills from unlabelled and unstructured demonstrations by learning skill segmentation and imitation learning jointly. The extensive simulation results indicate that our method can efficiently separate the demonstrations into individual skills and learn to imitate them using a single multi-modal policy. The video of our experiments is available at http://sites.google.com/view/nips17intentiongan

arXiv commentPaper accepted to NIPS 2017

References in corpus (11)

• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
• Deep multi-scale video prediction beyond mean square error
• Generative Adversarial Imitation Learning
• One-Shot Imitation Learning
• A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
• Stochastic Neural Networks for Hierarchical Reinforcement Learning
• Connecting Generative Adversarial Networks and Actor-Critic Methods
• Multi-Level Discovery of Deep Options
• Path Integral Guided Policy Search

Cited by in corpus (14)

• Deep Reinforcement Learning for the Control of Robotic Manipulation: A Focussed Mini-Review
• Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task
• Robust Imitation of Diverse Behaviors
• One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks
• Mutual Alignment Transfer Learning
• Multi-task Maximum Entropy Inverse Reinforcement Learning
• Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks
• Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation
• DDCO: Discovery of Deep Continuous Options for Robot Learning from Demonstrations
• Understanding Human Behaviors in Crowds by Imitating the Decision-Making Process
• Language Conditioned Imitation Learning over Unstructured Data
• Maximum Entropy Multi-Task Inverse RL
• Learning without Knowing: Unobserved Context in Continuous Transfer Reinforcement Learning
• Constraint Estimation and Derivative-Free Recovery for Robot Learning from Demonstrations