Programmatic Imitation Learning from Unlabeled and Noisy Demonstrations
Authors:
Preprint
Abstract
Imitation Learning (IL) is a promising paradigm for teaching robots to perform novel tasks using demonstrations. Most existing approaches for IL utilize neural networks (NN), however, these methods suffer from several well-known limitations: they 1) require large amounts of training data, 2) are hard to interpret, and 3) are hard to repair and adapt. There is an emerging interest in programmatic imitation learning (PIL), which offers significant promise in addressing the above limitations. In PIL, the learned policy is represented in a programming language, making it amenable to interpretation and repair. However, state-of-the-art PIL algorithms assume access to action labels and struggle to learn from noisy real-world demonstrations. In this paper, we propose PLUNDER, a novel PIL algorithm that integrates a probabilistic program synthesizer in an iterative Expectation-Maximization (EM) framework to address these shortcomings. Unlike existing PIL approaches, PLUNDER synthesizes probabilistic programmatic policies that are particularly well-suited for modeling the uncertainties inherent in real-world demonstrations. Our approach leverages an EM loop to simultaneously infer the missing action labels and the most likely probabilistic policy. We benchmark PLUNDER against several established IL techniques, and demonstrate its superiority across five challenging imitation learning tasks under noise. PLUNDER policies achieve 95% accuracy in matching the given demonstrations, outperforming the next best baseline by 19%. Additionally, policies generated by PLUNDER successfully complete the tasks 17% more frequently than the nearest baseline.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Diffusion policy: Visuomotor policy learning via action diffusionThe International Journal of Robotics Research, 2024
- Imitation Learning: Progress, Taxonomies and ChallengesIEEE Transactions on Neural Networks and Learning Systems, 2022
- Learning to Drive by Imitation: An Overview of Deep Behavior Cloning MethodsIEEE Transactions on Intelligent Vehicles, 2020
- Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience2019
- Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations2018
- The limits and potentials of deep learning for roboticsThe International Journal of Robotics Research, 2018
- Using probabilistic movement primitives in roboticsAutonomous Robots, 2017
- Probabilistic roboticsCommunications of the ACM, 2002
- Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learningArtificial Intelligence, 1999
- A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants1998