Closing the Closed-Loop Distribution Shift in Safe Imitation Learning

• URL: http://arxiv.org/abs/2102.09161v1
• Date: Thu, 18 Feb 2021 05:11:41 GMT
• Title: Closing the Closed-Loop Distribution Shift in Safe Imitation Learning
• Authors: Stephen Tu and Alexander Robey and Nikolai Matni
• Abstract summary: 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.
• Score: 80.05727171757454
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Commonly used optimization-based control strategies such as model-predictive and control Lyapunov/barrier function based controllers often enjoy provable stability, robustness, and safety properties. However, implementing such approaches requires solving optimization problems online at high-frequencies, which may not be possible on resource-constrained commodity hardware. Furthermore, how to extend the safety guarantees of such approaches to systems that use rich perceptual sensing modalities, such as cameras, remains unclear. In this paper, we address this gap by treating safe optimization-based control strategies as experts in an imitation learning problem, and train a learned policy that can be cheaply evaluated at run-time and that provably satisfies the same safety guarantees as the expert. In particular, we propose Constrained Mixing Iterative Learning (CMILe), a novel on-policy robust imitation learning algorithm that integrates ideas from stochastic mixing iterative learning, constrained policy optimization, and nonlinear robust control. Our approach allows us to control errors introduced by both the learning task of imitating an expert and by the distribution shift inherent to deviating from the original expert policy. The value of using tools from nonlinear robust control to impose stability constraints on learned policies is shown through sample-complexity bounds that are independent of the task time-horizon. We demonstrate the usefulness of CMILe through extensive experiments, including training a provably safe perception-based controller using a state-feedback-based expert.

Related papers

• Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning [64.11013095004786]
  We propose a dual-agent safe reinforcement learning strategy consisting of a baseline and a safe agent. Such a decoupled framework enables high flexibility, data efficiency and risk-awareness for RL-based control. The proposed method outperforms the state-of-the-art safe RL algorithms on difficult robot locomotion and manipulation tasks.
  arXiv  Detail & Related papers  (2022-12-14T03:11:25Z)
• Sample-efficient Safe Learning for Online Nonlinear Control with Control Barrier Functions [35.9713619595494]
  Reinforcement Learning and continuous nonlinear control have been successfully deployed in multiple domains of complicated sequential decision-making tasks. Given the exploration nature of the learning process and the presence of model uncertainty, it is challenging to apply them to safety-critical control tasks. We propose a emphprovably efficient episodic safe learning framework for online control tasks.
  arXiv  Detail & Related papers  (2022-07-29T00:54:35Z)
• Adaptive control of a mechatronic system using constrained residual reinforcement learning [0.0]
  We propose a simple, practical and intuitive approach to improve the performance of a conventional controller in uncertain environments. Our approach is motivated by the observation that conventional controllers in industrial motion control value robustness over adaptivity to deal with different operating conditions.
  arXiv  Detail & Related papers  (2021-10-06T08:13:05Z)
• Probabilistic robust linear quadratic regulators with Gaussian processes [73.0364959221845]
  Probabilistic models such as Gaussian processes (GPs) are powerful tools to learn unknown dynamical systems from data for subsequent use in control design. We present a novel controller synthesis for linearized GP dynamics that yields robust controllers with respect to a probabilistic stability margin.
  arXiv  Detail & Related papers  (2021-05-17T08:36:18Z)
• 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)
• Improper Learning with Gradient-based Policy Optimization [62.50997487685586]
  We consider an improper reinforcement learning setting where the learner is given M base controllers for an unknown Markov Decision Process. We propose a gradient-based approach that operates over a class of improper mixtures of the controllers.
  arXiv  Detail & Related papers  (2021-02-16T14:53:55Z)
• Enforcing robust control guarantees within neural network policies [76.00287474159973]
  We propose a generic nonlinear control policy class, parameterized by neural networks, that enforces the same provable robustness criteria as robust control. We demonstrate the power of this approach on several domains, improving in average-case performance over existing robust control methods and in worst-case stability over (non-robust) deep RL methods.
  arXiv  Detail & Related papers  (2020-11-16T17:14:59Z)
• Reinforcement Learning Control of Constrained Dynamic Systems with Uniformly Ultimate Boundedness Stability Guarantee [12.368097742148128]
  Reinforcement learning (RL) is promising for complicated nonlinear control problems. The data-based learning approach is notorious for not guaranteeing stability, which is the most fundamental property for any control system. In this paper, the classic Lyapunov's method is explored to analyze the uniformly ultimate boundedness stability (UUB) solely based on data.
  arXiv  Detail & Related papers  (2020-11-13T12:41:56Z)
• Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems [81.7983463275447]
  Learning-based control algorithms require data collection with abundant supervision for training. We present a new approach for optimal motion planning with safe exploration that integrates chance-constrained optimal control with dynamics learning and feedback control.
  arXiv  Detail & Related papers  (2020-05-09T05:57:43Z)

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.