mlsanityData to 14 Oct 2026

End-to-End Stable Imitation Learning via Autonomous Neural Dynamic Policies

arXiv 2305.12886 ↗First posted 22 May 2023cs.RO cs.AI cs.LGcited by 2

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

State-of-the-art sensorimotor learning algorithms offer policies that can often produce unstable behaviors, damaging the robot and/or the environment. Traditional robot learning, on the contrary, relies on dynamical system-based policies that can be analyzed for stability/safety. Such policies, however, are neither flexible nor generic and usually work only with proprioceptive sensor states. In this work, we bridge the gap between generic neural network policies and dynamical system-based policies, and we introduce Autonomous Neural Dynamic Policies (ANDPs) that: (a) are based on autonomous dynamical systems, (b) always produce asymptotically stable behaviors, and (c) are more flexible than traditional stable dynamical system-based policies. ANDPs are fully differentiable, flexible generic-policies that can be used in imitation learning setups while ensuring asymptotic stability. In this paper, we explore the flexibility and capacity of ANDPs in several imitation learning tasks including experiments with image observations. The results show that ANDPs combine the benefits of both neural network-based and dynamical system-based methods.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 7 of its 26 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

7 of 26 references.

Closest ancestors · 1

Same direction, newest first

  1. 2018An Algorithmic Perspective on Imitation Learning16 Nov

Other references · 6

  1. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 715
  2. 2019Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Taskscited by 67
  3. 2020Neural Dynamic Policies for End-to-End Sensorimotor Learningcited by 58
  4. 2018A survey on policy search algorithms for learning robot controllers in a handful of trialscited by 35
  5. 2019A Comparison of Action Spaces for Learning Manipulation Taskscited by 17
  6. 2021Hierarchical Neural Dynamic Policiescited by 17

Built on by

Cited by year

Citing papers per year: 2024: 2.

2 papers.

  1. 2024SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systemscited by 14
  2. 2024Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overviewcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2024Globally Stable Neural Imitation Policies
  2. 2024Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery
  3. 2023Memory-Consistent Neural Networks for Imitation Learning
  4. 2025The Pitfalls of Imitation Learning when Actions are Continuous
  5. 2023Learning Lyapunov-Stable Polynomial Dynamical Systems through Imitation
  6. 2019MANGA: Method Agnostic Neural-policy Generalization and Adaptation ↗
  7. 2019On-Policy Robot Imitation Learning from a Converging Supervisor
  8. 2025Elastic Motion Policy: An Adaptive Dynamical System for Robust and Efficient One-Shot Imitation Learning