arXiv (Cornell University) · 2017 · 60 citations · 19 references
EngineeringAutonomous SystemsCollective BehaviorComplex SystemsSwarm RoboticsImitation LearningLearning From DemonstrationPolicy LearningTeam LearningImitation From ObservationLearning From Imperfect DemonstrationsMulti-agent Imitation Learning
We study the problem of imitation learning from demonstrations of multiple coordinating agents. One key challenge in this setting is that learning a good model of coordination can be difficult, since coordination is often implicit in the demonstrations and must be inferred as a latent variable. We propose a joint approach that simultaneously learns a latent coordination model along with the individual policies. In particular, our method integrates unsupervised structure learning with conventional imitation learning. We illustrate the power of our approach on a difficult problem of learning multiple policies for fine-grained behavior modeling in team sports, where different players occupy different roles in the coordinated team strategy. We show that having a coordination model to infer the roles of players yields substantially improved imitation loss compared to conventional baselines.
19
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
Stochastic variational inference
Matthew D. Hoffman, David M. Blei, Chong Wang et al. · Journal of Machine Learning Research · 2013 · 1.5K citations
Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
Samy Bengio, Oriol Vinyals, Navdeep Jaitly et al. · arXiv (Cornell University) · 2015 · 1.3K citations · Full text