Equivalent and Compact Representations of Neural Network Controllers With Decision Trees

• URL: http://arxiv.org/abs/2304.06049v3
• Date: Fri, 18 Jul 2025 15:52:36 GMT
• Title: Equivalent and Compact Representations of Neural Network Controllers With Decision Trees
• Authors: Kevin Chang, Nathan Dahlin, Rahul Jain, Pierluigi Nuzzo,
• Abstract summary: We investigate the transformation of NN-based controllers into equivalent soft decision tree (SDT)-based controllers and its impact on verifiability.<n>We first demonstrate the practical efficacy of the transformation algorithm applied to an autonomous driving NN controller within OpenAI Gym's CarRacing environment.
• Score: 6.895161326320554
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Over the past decade, neural network (NN)-based controllers have demonstrated remarkable efficacy in a variety of decision-making tasks. However, their black-box nature and the risk of unexpected behaviors pose a challenge to their deployment in real-world systems requiring strong guarantees of correctness and safety. We address these limitations by investigating the transformation of NN-based controllers into equivalent soft decision tree (SDT)-based controllers and its impact on verifiability. In contrast to existing work, we focus on discrete-output NN controllers including rectified linear unit (ReLU) activation functions as well as argmax operations. We then devise an exact yet efficient transformation algorithm which automatically prunes redundant branches. We first demonstrate the practical efficacy of the transformation algorithm applied to an autonomous driving NN controller within OpenAI Gym's CarRacing environment. Subsequently, we evaluate our approach using two benchmarks from the OpenAI Gym environment. Our results indicate that the SDT transformation can benefit formal verification, showing runtime improvements of up to $21 \times$ and $2 \times$ for MountainCar-v0 and CartPole-v1, respectively.

Related papers

• Two-Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion [17.905596843865705]
  We propose a novel two-stage training framework to jointly synthesize the controller and Lyapunov function for continuous-time systems.<n>Unlike existing works on continuous-time systems that rely on an SMT solver to formally verify the Lyapunov condition, we extend state-of-the-art neural network verifier $alpha,!beta$-CROWN.
  arXiv  Detail & Related papers  (2025-06-02T06:20:09Z)
• Neural Network-assisted Interval Reachability for Systems with Control Barrier Function-Based Safe Controllers [1.77513002450736]
  Control Barrier Functions (CBFs) have been widely utilized in the design of optimization-based controllers and filters for dynamical systems. CBF-based controllers offer safety guarantees, but they can compromise the performance of the system. We propose a computationally efficient interval reachimatability method for performance verification of systems with optimization-based controllers.
  arXiv  Detail & Related papers  (2025-04-11T04:14:55Z)
• Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation [67.63756749551924]
  Learning-based neural network (NN) control policies have shown impressive empirical performance in a wide range of tasks in robotics and control. Lyapunov stability guarantees over the region-of-attraction (ROA) for NN controllers with nonlinear dynamical systems are challenging to obtain. We demonstrate a new framework for learning NN controllers together with Lyapunov certificates using fast empirical falsification and strategic regularizations.
  arXiv  Detail & Related papers  (2024-04-11T17:49:15Z)
• Optimal Controller Realizations against False Data Injections in Cooperative Driving [2.2134894590368748]
  We study a controller-oriented approach to mitigate the effect of a class of False-Data Injection (FDI) attacks. We show that a class of new but equivalent controllers can represent the base controller. We obtain the optimal combination of sensors that minimizes the effect of FDI attacks.
  arXiv  Detail & Related papers  (2024-04-08T09:53:42Z)
• Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution [51.83951489847344]
  In robotics applications, smooth control signals are commonly preferred to reduce system wear and energy efficiency. In this work, we aim to bridge this performance gap by growing discrete action spaces from coarse to fine control resolution. Our work indicates that an adaptive control resolution in combination with value decomposition yields simple critic-only algorithms that yield surprisingly strong performance on continuous control tasks.
  arXiv  Detail & Related papers  (2024-04-05T17:58:37Z)
• Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch [72.26822499434446]
  Auto-Train-Once (ATO) is an innovative network pruning algorithm designed to automatically reduce the computational and storage costs of DNNs. We provide a comprehensive convergence analysis as well as extensive experiments, and the results show that our approach achieves state-of-the-art performance across various model architectures.
  arXiv  Detail & Related papers  (2024-03-21T02:33:37Z)
• Structured Deep Neural Network-Based Backstepping Trajectory Tracking Control for Lagrangian Systems [9.61674297336072]
  The proposed controller can ensure closed-loop stability for any compatible neural network parameters. We show that in the presence of model approximation errors and external disturbances, the closed-loop stability and tracking control performance can still be guaranteed.
  arXiv  Detail & Related papers  (2024-03-01T09:09:37Z)
• Cal-DETR: Calibrated Detection Transformer [67.75361289429013]
  We propose a mechanism for calibrated detection transformers (Cal-DETR), particularly for Deformable-DETR, UP-DETR and DINO. We develop an uncertainty-guided logit modulation mechanism that leverages the uncertainty to modulate the class logits. Results corroborate the effectiveness of Cal-DETR against the competing train-time methods in calibrating both in-domain and out-domain detections.
  arXiv  Detail & Related papers  (2023-11-06T22:13:10Z)
• Sub-linear Regret in Adaptive Model Predictive Control [56.705978425244496]
  We present STT-MPC (Self-Tuning Tube-based Model Predictive Control), an online oracle that combines the certainty-equivalence principle and polytopic tubes. We analyze the regret of the algorithm, when compared to an algorithm initially aware of the system dynamics.
  arXiv  Detail & Related papers  (2023-10-07T15:07:10Z)
• Actor-Critic based Improper Reinforcement Learning [61.430513757337486]
  We consider an improper reinforcement learning setting where a learner is given $M$ base controllers for an unknown Markov decision process. We propose two algorithms: (1) a Policy Gradient-based approach; and (2) an algorithm that can switch between a simple Actor-Critic scheme and a Natural Actor-Critic scheme.
  arXiv  Detail & Related papers  (2022-07-19T05:55:02Z)
• Automated Repair of Neural Networks [0.26651200086513094]
  We introduce a framework for repairing unsafe NNs w.r.t. safety specification. Our method is able to search for a new, safe NN representation, by modifying only a few of its weight values. We perform extensive experiments which demonstrate the capability of our proposed framework to yield safe NNs w.r.t.
  arXiv  Detail & Related papers  (2022-07-17T12:42:24Z)
• Generating Probabilistic Safety Guarantees for Neural Network Controllers [30.34898838361206]
  We use a dynamics model to determine the output properties that must hold for a neural network controller to operate safely. We develop an adaptive verification approach to efficiently generate an overapproximation of the neural network policy. We show that our method is able to generate meaningful probabilistic safety guarantees for aircraft collision avoidance neural networks.
  arXiv  Detail & Related papers  (2021-03-01T18:48:21Z)
• Control of Stochastic Quantum Dynamics with Differentiable Programming [0.0]
  We propose a framework for the automated design of control schemes based on differentiable programming. We apply this approach to state preparation and stabilization of a qubit subjected to homodyne detection. Despite the resulting poor signal-to-noise ratio, we can train our controller to prepare and stabilize the qubit to a target state with a mean fidelity around 85%.
  arXiv  Detail & Related papers  (2021-01-04T19:00:03Z)
• DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search [55.164053971213576]
  convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead. Structured (channel) pruning is usually applied to reduce the model redundancy while preserving the network structure. Existing structured pruning methods require hand-crafted rules which may lead to tremendous pruning space.
  arXiv  Detail & Related papers  (2020-11-04T07:43:01Z)
• Optimizing Mixed Autonomy Traffic Flow With Decentralized Autonomous Vehicles and Multi-Agent RL [63.52264764099532]
  We study the ability of autonomous vehicles to improve the throughput of a bottleneck using a fully decentralized control scheme in a mixed autonomy setting. We apply multi-agent reinforcement algorithms to this problem and demonstrate that significant improvements in bottleneck throughput, from 20% at a 5% penetration rate to 33% at a 40% penetration rate, can be achieved.
  arXiv  Detail & Related papers  (2020-10-30T22:06:05Z)
• Controllable Orthogonalization in Training DNNs [96.1365404059924]
  Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1. This paper proposes a computationally efficient and numerically stable orthogonalization method using Newton's iteration (ONI) We show that our method improves the performance of image classification networks by effectively controlling the orthogonality to provide an optimal tradeoff between optimization benefits and representational capacity reduction. We also show that ONI stabilizes the training of generative adversarial networks (GANs) by maintaining the Lipschitz continuity of a network, similar to spectral normalization (
  arXiv  Detail & Related papers  (2020-04-02T10:14:27Z)

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.