Differentiable Robust LQR Layers

• URL: http://arxiv.org/abs/2106.05535v1
• Date: Thu, 10 Jun 2021 06:52:31 GMT
• Title: Differentiable Robust LQR Layers
• Authors: Ngo Anh Vien and Gerhard Neumann
• Abstract summary: This paper proposes a differentiable robust LQR layer for reinforcement learning and imitation learning under model uncertainty and dynamics. It provides a new type of inductive bias fority and uncertainty modeling in control systems. Experiment results show that the proposed method can optimize robust policies under uncertain situations.
• Score: 26.67150576276949
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This paper proposes a differentiable robust LQR layer for reinforcement learning and imitation learning under model uncertainty and stochastic dynamics. The robust LQR layer can exploit the advantages of robust optimal control and model-free learning. It provides a new type of inductive bias for stochasticity and uncertainty modeling in control systems. In particular, we propose an efficient way to differentiate through a robust LQR optimization program by rewriting it as a convex program (i.e. semi-definite program) of the worst-case cost. Based on recent work on using convex optimization inside neural network layers, we develop a fully differentiable layer for optimizing this worst-case cost, i.e. we compute the derivative of a performance measure w.r.t the model's unknown parameters, model uncertainty and stochasticity parameters. We demonstrate the proposed method on imitation learning and approximate dynamic programming on stochastic and uncertain domains. The experiment results show that the proposed method can optimize robust policies under uncertain situations, and are able to achieve a significantly better performance than existing methods that do not model uncertainty directly.

Related papers

• A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning [74.80956524812714]
  We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning. These problems are often formalized as Bi-Level optimizations (BLO) We introduce a novel perspective by turning a given BLO problem into a ii optimization, where the inner loss function becomes a smooth distribution, and the outer loss becomes an expected loss over the inner distribution.
  arXiv  Detail & Related papers  (2024-10-14T12:10:06Z)
• Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior [51.60683890503293]
  We propose a theoretical framework for studying behavior cloning of complex expert demonstrations using generative modeling. We show that pure supervised cloning can generate trajectories matching the per-time step distribution of arbitrary expert trajectories.
  arXiv  Detail & Related papers  (2023-07-27T04:27:26Z)
• Robust Regression via Model Based Methods [13.300549123177705]
  We propose an algorithm inspired by so-called model-based optimization (MBO) [35, 36], which replaces a non-objective with a convex model function. We apply this to robust regression, proposing SADM, a function of the Online Alternating Direction Method of Multipliers (OOADM) [50] to solve the inner optimization in MBO. Finally, we demonstrate experimentally (a) the robustness of l_p norms to outliers and (b) the efficiency of our proposed model-based algorithms in comparison with methods on autoencoders and multi-target regression.
  arXiv  Detail & Related papers  (2021-06-20T21:45:35Z)
• 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)
• Fast Distributionally Robust Learning with Variance Reduced Min-Max Optimization [85.84019017587477]
  Distributionally robust supervised learning is emerging as a key paradigm for building reliable machine learning systems for real-world applications. Existing algorithms for solving Wasserstein DRSL involve solving complex subproblems or fail to make use of gradients. We revisit Wasserstein DRSL through the lens of min-max optimization and derive scalable and efficiently implementable extra-gradient algorithms.
  arXiv  Detail & Related papers  (2021-04-27T16:56:09Z)
• Modeling the Second Player in Distributionally Robust Optimization [90.25995710696425]
  We argue for the use of neural generative models to characterize the worst-case distribution. This approach poses a number of implementation and optimization challenges. We find that the proposed approach yields models that are more robust than comparable baselines.
  arXiv  Detail & Related papers  (2021-03-18T14:26:26Z)
• Data-Driven Robust Optimization using Unsupervised Deep Learning [0.0]
  We show that a trained neural network can be integrated into a robust optimization model by formulating the adversarial problem as a convex mixed-integer program. We find that this approach outperforms a similar approach using kernel-based support vector sets.
  arXiv  Detail & Related papers  (2020-11-19T11:06:54Z)
• Logistic Q-Learning [87.00813469969167]
  We propose a new reinforcement learning algorithm derived from a regularized linear-programming formulation of optimal control in MDPs. The main feature of our algorithm is a convex loss function for policy evaluation that serves as a theoretically sound alternative to the widely used squared Bellman error.
  arXiv  Detail & Related papers  (2020-10-21T17:14:31Z)
• Uncertainty Modelling in Risk-averse Supply Chain Systems Using Multi-objective Pareto Optimization [0.0]
  One of the arduous tasks in supply chain modelling is to build robust models against irregular variations. We have introduced a novel methodology namely, Pareto Optimization to handle uncertainties and bound the entropy of such uncertainties by explicitly modelling them under some apriori assumptions.
  arXiv  Detail & Related papers  (2020-04-24T21:04:25Z)

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.