Corpus ID: 203642129

Learning Calibratable Policies using Programmatic Style-Consistency

  title={Learning Calibratable Policies using Programmatic Style-Consistency},
  author={Eric Zhan and Albert Tseng and Yisong Yue and A. Swaminathan and Matthew J. Hausknecht},
  • Eric Zhan, Albert Tseng, +2 authors Matthew J. Hausknecht
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • We study the important and challenging problem of controllable generation of long-term sequential behaviors. Solutions to this problem would impact many applications, such as calibrating behaviors of AI agents in games or predicting player trajectories in sports. In contrast to the well-studied areas of controllable generation of images, text, and speech, there are significant challenges that are unique to or exacerbated by generating long-term behaviors: how should we specify the factors of… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper


    Publications referenced by this paper.
    Generating Multi-Agent Trajectories using Programmatic Weak Supervision
    • 20
    • PDF
    Dynamics-Aware Unsupervised Discovery of Skills
    • 34
    • PDF
    Generating Long-term Trajectories Using Deep Hierarchical Networks
    • 56
    • PDF
    Robust Imitation of Diverse Behaviors
    • 85
    • Highly Influential
    • PDF
    A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
    • 1,212
    • PDF
    InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
    • 155
    • Highly Influential
    • PDF
    Diverse Generation for Multi-Agent Sports Games
    • 19
    • PDF
    Hierarchical Imitation and Reinforcement Learning
    • 64
    • PDF
    Generative Adversarial Imitation Learning
    • 826
    • PDF