History Encoding Representation Design for Human Intention Inference

Abstract

In this extended abstract, we investigate the design of learning representation for human intention inference. In our designed human intention prediction task, we propose a history encoding representation that is both interpretable and effective for prediction. Through extensive experiments, we show our prediction framework with a history encoding representation design is successful on the human intention prediction problem.

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Guided Policy Search Model-based Reinforcement Learning for Urban Autonomous Driving
• Cascade Attribute Learning Network
• Cascade Attribute Network: Decomposing Reinforcement Learning Control Policies using Hierarchical Neural Networks