Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation
arXiv:1707.03374
Abstract
Imitation learning is an effective approach for autonomous systems to acquire control policies when an explicit reward function is unavailable, using supervision provided as demonstrations from an expert, typically a human operator. However, standard imitation learning methods assume that the agent receives examples of observation-action tuples that could be provided, for instance, to a supervised learning algorithm. This stands in contrast to how humans and animals imitate: we observe another person performing some behavior and then figure out which actions will realize that behavior, compensating for changes in viewpoint, surroundings, object positions and types, and other factors. We term this kind of imitation learning "imitation-from-observation," and propose an imitation learning method based on video prediction with context translation and deep reinforcement learning. This lifts the assumption in imitation learning that the demonstration should consist of observations in the same environment configuration, and enables a variety of interesting applications, including learning robotic skills that involve tool use simply by observing videos of human tool use. Our experimental results show the effectiveness of our approach in learning a wide range of real-world robotic tasks modeled after common household chores from videos of a human demonstrator, including sweeping, ladling almonds, pushing objects as well as a number of tasks in simulation.
arXiv commentAccepted at ICRA 2018, Brisbane. YuXuan Liu and Abhishek Gupta had equal contribution
References in corpus (10)
- End to End Learning for Self-Driving Cars
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
- Generative Adversarial Imitation Learning
- Third-Person Imitation Learning
- InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
- Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning
- Time-Contrastive Networks: Self-Supervised Learning from Video
- Robobarista: Learning to Manipulate Novel Objects via Deep Multimodal Embedding
- Learning Robot Activities from First-Person Human Videos Using Convolutional Future Regression
Cited by in corpus (8)
- One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning
- Reinforcement and Imitation Learning for Diverse Visuomotor Skills
- Time-Contrastive Networks: Self-Supervised Learning from Video
- Reinforced Imitation in Heterogeneous Action Space
- Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency
- Motion2Vec: Semi-Supervised Representation Learning from Surgical Videos
- Learning to Run with Potential-Based Reward Shaping and Demonstrations from Video Data
- Manipulator-Independent Representations for Visual Imitation