Skip to yearly menu bar Skip to main content


Generating Long-term Trajectories Using Deep Hierarchical Networks

Stephan Zheng · Yisong Yue · Patrick Lucey

Area 5+6+7+8 #72

Keywords: [ Reinforcement Learning Algorithms ] [ Deep Learning or Neural Networks ]


We study the problem of modeling spatiotemporal trajectories over long time horizons using expert demonstrations. For instance, in sports, agents often choose action sequences with long-term goals in mind, such as achieving a certain strategic position. Conventional policy learning approaches, such as those based on Markov decision processes, generally fail at learning cohesive long-term behavior in such high-dimensional state spaces, and are only effective when fairly myopic decision-making yields the desired behavior. The key difficulty is that conventional models are ``single-scale'' and only learn a single state-action policy. We instead propose a hierarchical policy class that automatically reasons about both long-term and short-term goals, which we instantiate as a hierarchical neural network. We showcase our approach in a case study on learning to imitate demonstrated basketball trajectories, and show that it generates significantly more realistic trajectories compared to non-hierarchical baselines as judged by professional sports analysts.

Live content is unavailable. Log in and register to view live content