Infeasible optimization problems and the hierarchical augmented Lagrangian method in imitation learning

• URL: http://arxiv.org/abs/2606.00730v1
• Date: Sat, 30 May 2026 13:50:04 GMT
• Title: Infeasible optimization problems and the hierarchical augmented Lagrangian method in imitation learning
• Abstract summary: We study a simple remedy for such situations based on recent theoretical results on the augmented Lagrangian method in infeasible settings.<n>We show that our approach drives the learned policy toward the solution of a closest-feasible constrained IL problem with desirable properties.<n>The method is illustrated on a toy driving example with a total-acceleration constraint and pedestrian-safety constraints, a setting in which infeasibility can naturally arise while still allowing a safe learned policy.
• Score: 9.333654357828417
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Imitation learning (IL) is an effective approach to train complex robotics policies. Recent works have introduced hard constraints into imitation-learning optimization problems to ensure safety, stability, and robustness of the learned policy. However, we argue that these constraints are sometimes infeasible, which can lead to unstable or difficult training dynamics. We study a simple remedy for such situations based on recent theoretical results on the augmented Lagrangian method in infeasible settings. We show that our approach drives the learned policy toward the solution of a closest-feasible constrained IL problem with desirable properties. The method is illustrated on a toy driving example with a total-acceleration constraint and pedestrian-safety constraints, a setting in which infeasibility can naturally arise while still allowing a safe learned policy.

Related papers

• Directional Constraints for Efficient Exploration in Safe Reinforcement Learning [19.03722256244529]
  We propose an extension of the ATACOM framework to enforce constraints derived from prior knowledge of the system or learned directly from data.<n>Our proposed method, named ATACOM Directional Constraints (ATACOM-DC), significantly improves the safety-performance trade-off.<n>We evaluate our method across a range of challenging robotic control tasks in simulation, analyzing both constraint-violation costs and achieved task performance.
  arXiv  Detail & Related papers  (2026-07-14T13:59:20Z)
• Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning [7.888219789657414]
  In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints.<n>We address these issues with a novel approach that begins by learning a conservatively safe policy through the use of Conditional Variational Autoencoders.<n>We frame this as a Constrained Reward-Return Maximization problem, wherein the policy aims to optimize rewards while complying with the inferred latent safety constraints.
  arXiv  Detail & Related papers  (2024-12-11T22:00:07Z)
• RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes [57.319845580050924]
  We propose a reinforcement learning framework that combines risk-sensitive control with an adaptive action space curriculum. We show that our algorithm is capable of learning high-speed policies for a real-world off-road driving task.
  arXiv  Detail & Related papers  (2024-05-07T23:32:36Z)
• Constrained Meta-Reinforcement Learning for Adaptable Safety Guarantee with Differentiable Convex Programming [4.825619788907192]
  This paper studies the unique challenges of ensuring safety in non-stationary environments by solving constrained problems through the lens of the meta-learning approach (learning-to-learn) We first employ successive convex-constrained policy updates across multiple tasks with differentiable convexprogramming, which allows meta-learning in constrained scenarios by enabling end-to-end differentiation.
  arXiv  Detail & Related papers  (2023-12-15T21:55:43Z)
• Resilient Constrained Learning [94.27081585149836]
  This paper presents a constrained learning approach that adapts the requirements while simultaneously solving the learning task. We call this approach resilient constrained learning after the term used to describe ecological systems that adapt to disruptions by modifying their operation.
  arXiv  Detail & Related papers  (2023-06-04T18:14:18Z)
• Safety-Constrained Policy Transfer with Successor Features [19.754549649781644]
  We propose a Constrained Markov Decision Process (CMDP) formulation that enables the transfer of policies and adherence to safety constraints. Our approach relies on a novel extension of generalized policy improvement to constrained settings via a Lagrangian formulation. Our experiments in simulated domains show that our approach is effective; it visits unsafe states less frequently and outperforms alternative state-of-the-art methods when taking safety constraints into account.
  arXiv  Detail & Related papers  (2022-11-10T06:06:36Z)
• Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments [84.3830478851369]
  We propose a safe reinforcement learning approach that can jointly learn the environment and optimize the control policy. Our approach can effectively enforce hard safety constraints and significantly outperform CMDP-based baseline methods in system safe rate measured via simulations.
  arXiv  Detail & Related papers  (2022-09-29T20:49:25Z)
• On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI Conditions [3.296303220677533]
  We formulate the imitation learning of linear policies as a constrained optimization problem. We show that one can guarantee the closed-loop stability and robustness by posing linear matrix inequality (LMI) constraints on the fitted policy.
  arXiv  Detail & Related papers  (2021-03-24T02:43:03Z)
• State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards [88.30521204048551]
  A common formulation of constrained reinforcement learning involves multiple rewards that must individually accumulate to given thresholds. We show a simple example in which the desired optimal policy cannot be induced by any weighted linear combination of rewards. This work addresses this shortcoming by augmenting the state with Lagrange multipliers and reinterpreting primal-dual methods.
  arXiv  Detail & Related papers  (2021-02-23T21:07:35Z)
• Closing the Closed-Loop Distribution Shift in Safe Imitation Learning [80.05727171757454]
  We treat safe optimization-based control strategies as experts in an imitation learning problem. We train a learned policy that can be cheaply evaluated at run-time and that provably satisfies the same safety guarantees as the expert.
  arXiv  Detail & Related papers  (2021-02-18T05:11:41Z)
• Probably Approximately Correct Constrained Learning [135.48447120228658]
  We develop a generalization theory based on the probably approximately correct (PAC) learning framework. We show that imposing a learner does not make a learning problem harder in the sense that any PAC learnable class is also a constrained learner. We analyze the properties of this solution and use it to illustrate how constrained learning can address problems in fair and robust classification.
  arXiv  Detail & Related papers  (2020-06-09T19:59:29Z)

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.