The Pitfalls of Imitation Learning when Actions are Continuous

This is experimental HTML to improve accessibility. We invite you to report rendering errors. Use Alt+Y to toggle on accessible reporting links and Alt+Shift+Y to toggle off. Learn more about this project and help improve conversions.

The Pitfalls of Imitation Learning when Actions are Continuous The Pitfalls of Imitation Learning when Actions are Continuous Max Simchowitz 1 1 1 msimchow@andrew.cmu.edu CMU Daniel Pfrommer 2 2 2 dpfrom@mit.edu MIT Ali Jadbabaie 3 3 3 jadbabai@mit.edu MIT (July 26, 2025) Abstract We study the problem of imitating an expert demonstrator in a discrete-time, continuous state-and-action control system. We show that, even if the dynamics satisfy a control-theoretic property called exponential stability (i.e. the effects of perturbations decay exponentially quickly), and the expert is smooth and de

related reading

• Ch. 21 - Imitation Learningunderactuated.mit.edu
• Learning to Imitate | SAIL Blogai.stanford.edu
• 1011.0686arxiv.org
• [2507.09061] Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Controlarxiv.org
• State of Robot Learning, December 2025vedder.io
• Generative Adversarial Imitation Learning.pdfcs.stanford.edu
• Life lessons from reinforcement learning - Jason Weijasonwei.net
• Reinforcement Learning via Implicit Imitation Guidancearxiv.org
• Imitating Latent Policies from Observationarxiv.org
• Should I Use Offline RL or Imitation Learning? – The Berkeley Artificial Intelligence Research Blogbair.berkeley.edu
• Generative Adversarial Imitation Learningarxiv.org
• [2606.09758] Difference-Aware Retrieval Policies for Imitation Learningarxiv.org