Exact and Cost-Effective Automated Transformation of Neural Network Controllers to Decision Tree Controllers
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 and surprising results pose a challenge to their deployment in real-world systems with 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. Differently from previous approaches, we focus on discrete-output NN controllers including rectified linear unit (ReLU) activation functions as well as argmax operations. We then devise an exact but cost-effective transformation algorithm, in that it can automatically prune redundant branches. 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 21x and 2x for MountainCar-v0 and CartPole-v0, respectively.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingOpenAI GymSimilar Papers 제목 키워드 기반
Fine-Tuning Language Models Using Formal Methods Feedback
Although pre-trained language models encode generic knowledge beneficial for planning and control, they may fail to generate appropriate control policies for domain-specific tasks. Existing fine-tuning methods use human …
Autonomous DrivingDual adaptive MPC using an exact set-membership reformulation
Adaptive model predictive control (MPC) methods using set-membership identification to reduce parameter uncertainty are considered in this work. Strong duality is used to reformulate the set-membership equations exactly …
Model Predictive ControlScalable Synthesis of Verified Controllers in Deep Reinforcement Learning
There has been significant recent interest in devising verification techniques for learning-enabled controllers (LECs) that manage safety-critical systems. Given the opacity and lack of interpretability of the neural pol…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)GPT-FT: An Efficient Automated Feature Transformation Using GPT for Sequence Reconstruction and Performance Enhancement
Feature transformation plays a critical role in enhancing machine learning model performance by optimizing data representations. Recent state-of-the-art approaches address this task as a continuous embedding optimization…
Computational EfficiencyA Vehicle-in-the-Loop Simulator with AI-Powered Digital Twins for Testing Automated Driving Controllers
Simulators are useful tools for testing automated driving controllers. Vehicle-in-the-loop (ViL) tests and digital twins (DTs) are widely used simulation technologies to facilitate the smooth deployment of controllers to…
Autonomous Vehicles