Robust Behavior Cloning Via Global Lipschitz Regularization

• URL: http://arxiv.org/abs/2506.19250v1
• Date: Tue, 24 Jun 2025 02:19:08 GMT
• Title: Robust Behavior Cloning Via Global Lipschitz Regularization
• Authors: Shili Wu, Yizhao Jin, Puhua Niu, Aniruddha Datta, Sean B. Andersson,
• Abstract summary: Behavior Cloning is an effective imitation learning technique and has even been adopted in some safety-critical domains such as autonomous vehicles.<n>We use a global Lipschitz regularization approach to enhance the robustness of the learned policy network.<n>We propose a way to construct a Lipschitz neural network that ensures the policy robustness.
• Score: 0.5767156832161817
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Behavior Cloning (BC) is an effective imitation learning technique and has even been adopted in some safety-critical domains such as autonomous vehicles. BC trains a policy to mimic the behavior of an expert by using a dataset composed of only state-action pairs demonstrated by the expert, without any additional interaction with the environment. However, During deployment, the policy observations may contain measurement errors or adversarial disturbances. Since the observations may deviate from the true states, they can mislead the agent into making sub-optimal actions. In this work, we use a global Lipschitz regularization approach to enhance the robustness of the learned policy network. We then show that the resulting global Lipschitz property provides a robustness certificate to the policy with respect to different bounded norm perturbations. Then, we propose a way to construct a Lipschitz neural network that ensures the policy robustness. We empirically validate our theory across various environments in Gymnasium. Keywords: Robust Reinforcement Learning; Behavior Cloning; Lipschitz Neural Network

Related papers

• How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation [17.638831964639834]
  Behavior cloning policies are increasingly successful at solving complex tasks by learning from human demonstrations. We present a framework that provides a tight lower-bound on robot performance in an arbitrary environment. In experiments we evaluate policies for visuomotor manipulation in both simulation and hardware.
  arXiv  Detail & Related papers  (2024-05-08T22:00:35Z)
• Invariant Causal Imitation Learning for Generalizable Policies [87.51882102248395]
  We propose Invariant Causal Learning (ICIL) to learn an imitation policy. ICIL learns a representation of causal features that is disentangled from the specific representations of noise variables. We show that ICIL is effective in learning imitation policies capable of generalizing to unseen environments.
  arXiv  Detail & Related papers  (2023-11-02T16:52:36Z)
• Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms [79.61176746380718]
  Multi-Agent Reinforcement Learning (MARL) has shown promising results across several domains. MARL policies often lack robustness and are sensitive to small changes in their environment. We show that we can gain robustness by controlling a policy's Lipschitz constant. We propose a new robust MARL framework, ERNIE, that promotes the Lipschitz continuity of the policies.
  arXiv  Detail & Related papers  (2023-10-16T20:14:06Z)
• Coherent Soft Imitation Learning [17.345411907902932]
  Imitation learning methods seek to learn from an expert either through behavioral cloning (BC) of the policy or inverse reinforcement learning (IRL) of the reward. This work derives an imitation method that captures the strengths of both BC and IRL.
  arXiv  Detail & Related papers  (2023-05-25T21:54:22Z)
• Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching [109.5084863685397]
  offline imitation learning (IL) promises the ability to learn performant policies from pre-collected demonstrations without interactions with the environment. We present RelaxDICE, which employs an asymmetrically-relaxed f-divergence for explicit support regularization. Our method significantly outperforms the best prior offline method in six standard continuous control environments.
  arXiv  Detail & Related papers  (2023-03-05T03:35:11Z)
• Hallucinated Adversarial Control for Conservative Offline Policy Evaluation [64.94009515033984]
  We study the problem of conservative off-policy evaluation (COPE) where given an offline dataset of environment interactions, we seek to obtain a (tight) lower bound on a policy's performance. We introduce HAMBO, which builds on an uncertainty-aware learned model of the transition dynamics. We prove that the resulting COPE estimates are valid lower bounds, and, under regularity conditions, show their convergence to the true expected return.
  arXiv  Detail & Related papers  (2023-03-02T08:57:35Z)
• Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints [82.43359506154117]
  We show that typical offline reinforcement learning methods fail to learn from data with non-uniform variability. Our method is simple, theoretically motivated, and improves performance across a wide range of offline RL problems in Atari games, navigation, and pixel-based manipulation.
  arXiv  Detail & Related papers  (2022-11-02T11:36:06Z)
• Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds [99.23098204458336]
  Certified robustness is a desirable property for deep neural networks in safety-critical applications. We show that our method consistently outperforms state-of-the-art methods on MNIST and TinyNet datasets.
  arXiv  Detail & Related papers  (2021-11-02T06:44:10Z)
• On the Benefits of Inducing Local Lipschitzness for Robust Generative Adversarial Imitation Learning [36.48610705372544]
  We study the effect of local Lipschitzness of the discriminator and the generator on the robustness of policies learned by GAIL. We show that the modified objective leads to learning significantly more robust policies.
  arXiv  Detail & Related papers  (2021-06-30T21:48:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.