arXiv subjects

Shengbo Wang

Publications and source records attributed to Shengbo Wang.

48 records · Page 3Linked to original sources

arXiv2024

A Finite Sample Complexity Bound for Distributionally Robust Q-learning

We consider a reinforcement learning setting in which the deployment environment is different from the training environment. Applying a robust Markov decision processes formulation, we extend the distributionally robust $Q$-learning framework studied in Liu et al. [2022]. Further, we improve the design and analysis of their multi-level Monte Carlo estimator. Assuming access to a simulator, we prove that the worst-case expected sample complexity of our algorithm to learn the optimal robust $Q$-function within an $ε$ error in the sup norm is upper bounded by $\tilde O(|S||A|(1-γ)^{-5}ε^{-2}p_{\wedge}^{-6}δ^{-4})$, where $γ$ is the discount rate, $p_{\wedge}$ is the non-zero minimal support probability of the transition kernels and $δ$ is the uncertainty size. This is the first sample complexity result for the model-free robust RL problem. Simulation studies further validate our theoretical results.

cs.LG↗

arXiv2024

Self-reconfigurable Multifunctional Memristive Nociceptor for Intelligent Robotics

Artificial nociceptors, mimicking human-like stimuli perception, are of significance for intelligent robotics to work in hazardous and dynamic scenarios. One of the most essential characteristics of the human nociceptor is its self-adjustable attribute, which indicates that the threshold of determination of a potentially hazardous stimulus relies on environmental knowledge. This critical attribute has been currently omitted, but it is highly desired for artificial nociceptors. Inspired by these shortcomings, this article presents, for the first time, a Self-Directed Channel (SDC) memristor-based self-reconfigurable nociceptor, capable of perceiving hazardous pressure stimuli under different temperatures and demonstrates key features of tactile nociceptors, including 'threshold,' 'no-adaptation,' and 'sensitization.' The maximum amplification of hazardous external stimuli is 1000%, and its response characteristics dynamically adapt to current temperature conditions by automatically altering the generated modulation schemes for the memristor. The maximum difference ratio of the response of memristors at different temperatures is 500%, and this adaptability closely mimics the functions of biological tactile nociceptors, resulting in accurate danger perception in various conditions. Beyond temperature adaptation, this memristor-based nociceptor has the potential to integrate different sensory modalities by applying various sensors, thereby achieving human-like perception capabilities in real-world environments.

physics.app-ph↗

arXiv2024

Real-Time State Modulation and Acquisition Circuit in Neuromorphic Memristive Systems

Memristive neuromorphic systems are designed to emulate human perception and cognition, where the memristor states represent essential historical information to perform both low-level and high-level tasks. However, current systems face challenges with the separation of state modulation and acquisition, leading to undesired time delays that impact real-time performance. To overcome this issue, we introduce a dual-function circuit that concurrently modulates and acquires memristor state information. This is achieved through two key features: 1) a feedback operational amplifier (op-amp) based circuit that ensures precise voltage application on the memristor while converting the passing current into a voltage signal; 2) a division calculation circuit that acquires state information from the modulation voltage and the converted voltage, improving stability by leveraging the intrinsic threshold characteristics of memristors. This circuit has been evaluated in a memristor-based nociceptor and a memristor crossbar, demonstrating exceptional performance. For instance, it achieves mean absolute acquisition errors below 1 Ω during the modulation process in the nociceptor application. These results demonstrate that the proposed circuit can operate at different scales, holding the potential to enhance a wide range of neuromorphic applications.

physics.app-ph↗

arXiv2024

Lightweight, error-tolerant edge detection using memristor-enabled stochastic logics

The demand for efficient edge vision has spurred the interest in developing stochastic computing approaches for performing image processing tasks. Memristors with inherent stochasticity readily introduce probability into the computations and thus enable stochastic image processing computations. Here, we present a stochastic computing approach for edge detection, a fundamental image processing technique, facilitated with memristor-enabled stochastic logics. Specifically, we integrate the memristors with logic circuits and harness the stochasticity from the memristors to realize compact stochastic logics for stochastic number encoding and processing. The stochastic numbers, exhibiting well-regulated probabilities and correlations, can be processed to perform logic operations with statistical probabilities. This can facilitate lightweight stochastic edge detection for edge visual scenarios characterized with high-level noise errors. As a practical demonstration, we implement a hardware stochastic Roberts cross operator using the stochastic logics, and prove its exceptional edge detection performance, remarkably, with 95% less computational cost while withstanding 50% bit-flip errors. The results underscore the great potential of our stochastic edge detection approach in developing lightweight, error-tolerant edge vision hardware and systems for autonomous driving, virtual/augmented reality, medical imaging diagnosis, industrial automation, and beyond.

cs.ET↗

arXiv2024

Optimal Sample Complexity for Average Reward Markov Decision Processes

We resolve the open question regarding the sample complexity of policy learning for maximizing the long-run average reward associated with a uniformly ergodic Markov decision process (MDP), assuming a generative model. In this context, the existing literature provides a sample complexity upper bound of $\widetilde O(|S||A|t_{\text{mix}}^2 ε^{-2})$ and a lower bound of $Ω(|S||A|t_{\text{mix}} ε^{-2})$. In these expressions, $|S|$ and $|A|$ denote the cardinalities of the state and action spaces respectively, $t_{\text{mix}}$ serves as a uniform upper limit for the total variation mixing times, and $ε$ signifies the error tolerance. Therefore, a notable gap of $t_{\text{mix}}$ still remains to be bridged. Our primary contribution is the development of an estimator for the optimal policy of average reward MDPs with a sample complexity of $\widetilde O(|S||A|t_{\text{mix}}ε^{-2})$. This marks the first algorithm and analysis to reach the literature's lower bound. Our new algorithm draws inspiration from ideas in Li et al. (2020), Jin and Sidford (2021), and Wang et al. (2023). Additionally, we conduct numerical experiments to validate our theoretical findings.

cs.LG↗

arXiv2023

Constrained Bayesian Optimization Under Partial Observations: Balanced Improvements and Provable Convergence

The partially observable constrained optimization problems (POCOPs) impede data-driven optimization techniques since an infeasible solution of POCOPs can provide little information about the objective as well as the constraints. We endeavor to design an efficient and provable method for expensive POCOPs under the framework of constrained Bayesian optimization. Our method consists of two key components. Firstly, we present an improved design of the acquisition functions that introduces balanced exploration during optimization. We rigorously study the convergence properties of this design to demonstrate its effectiveness. Secondly, we propose a Gaussian process embedding different likelihoods as the surrogate model for a partially observable constraint. This model leads to a more accurate representation of the feasible regions compared to traditional classification-based models. Our proposed method is empirically studied on both synthetic and real-world problems. The results demonstrate the competitiveness of our method for solving POCOPs.

cs.LG↗

arXiv2023

Intelligent machines work in unstructured environments by differential neuromorphic computing

Efficient operation of intelligent machines in the real world requires methods that allow them to understand and predict the uncertainties presented by the unstructured environments with good accuracy, scalability and generalization, similar to humans. Current methods rely on pretrained networks instead of continuously learning from the dynamic signal properties of working environments and suffer inherent limitations, such as data-hungry procedures, and limited generalization capabilities. Herein, we present a memristor-based differential neuromorphic computing, perceptual signal processing and learning method for intelligent machines. The main features of environmental information such as amplification (>720%) and adaptation (<50%) of mechanical stimuli encoded in memristors, are extracted to obtain human-like processing in unstructured environments. The developed method takes advantage of the intrinsic multi-state property of memristors and exhibits good scalability and generalization, as confirmed by validation in two different application scenarios: object grasping and autonomous driving. In the former, a robot hand experimentally realizes safe and stable grasping through fast learning (in ~1 ms) the unknown object features (e.g., sharp corner and smooth surface) with a single memristor. In the latter, the decision-making information of 10 unstructured environments in autonomous driving (e.g., overtaking cars, pedestrians) is accurately (94%) extracted with a 40*25 memristor array. By mimicking the intrinsic nature of human low-level perception mechanisms, the electronic memristive neuromorphic circuit-based method, presented here shows the potential for adapting to diverse sensing technologies and helping intelligent machines generate smart high-level decisions in the real world.

eess.SP↗

arXiv2023

Model-Assisted Probabilistic Safe Adaptive Control With Meta-Bayesian Learning

Breaking safety constraints in control systems can lead to potential risks, resulting in unexpected costs or catastrophic damage. Nevertheless, uncertainty is ubiquitous, even among similar tasks. In this paper, we develop a novel adaptive safe control framework that integrates meta learning, Bayesian models, and control barrier function (CBF) method. Specifically, with the help of CBF method, we learn the inherent and external uncertainties by a unified adaptive Bayesian linear regression (ABLR) model, which consists of a forward neural network (NN) and a Bayesian output layer. Meta learning techniques are leveraged to pre-train the NN weights and priors of the ABLR model using data collected from historical similar tasks. For a new control task, we refine the meta-learned models using a few samples, and introduce pessimistic confidence bounds into CBF constraints to ensure safe control. Moreover, we provide theoretical criteria to guarantee probabilistic safety during the control processes. To validate our approach, we conduct comparative experiments in various obstacle avoidance scenarios. The results demonstrate that our algorithm significantly improves the Bayesian model-based CBF method, and is capable for efficient safe exploration even with multiple uncertain constraints.

eess.SY↗

arXiv2023

Suboptimal Safety-Critical Control for Continuous Systems Using Prediction-Correction Online Optimization

This paper investigates the control barrier function (CBF) based safety-critical control for continuous nonlinear control affine systems using the more efficient online algorithms through time-varying optimization. The idea lies in that when quadratic programming (QP) or other convex optimization algorithms needed in the CBF-based method is not computation affordable, the alternative suboptimal feasible solutions can be obtained more economically. By using the barrier-based interior point method, the constrained CBF-QP problems are converted into the unconstrained ones with suboptimal solutions tracked by two continuous descent-based algorithms. Considering the lag effect of tracking and exploiting the system information, the prediction method is added to the algorithms which thereby achieves a exponential convergence rate to the time-varying suboptimal solutions. The convergence and robustness of the designed methods as well as the safety criteria of the algorithms are analyzed theoretically. In the end, the effectiveness is illustrated by simulations on the anti-swing and obstacle avoidance tasks.

eess.SY↗

arXiv2023

AutoGMap: Learning to Map Large-scale Sparse Graphs on Memristive Crossbars

The sparse representation of graphs has shown great potential for accelerating the computation of graph applications (e.g., Social Networks, Knowledge Graphs) on traditional computing architectures (CPU, GPU, or TPU). But the exploration of large-scale sparse graph computing on processing-in-memory (PIM) platforms (typically with memristive crossbars) is still in its infancy. To implement the computation or storage of large-scale or batch graphs on memristive crossbars, a natural assumption is that a large-scale crossbar is demanded, but with low utilization. Some recent works question this assumption, to avoid the waste of storage and computational resource, the fixed-size or progressively scheduled ''block partition'' schemes are proposed. However, these methods are coarse-grained or static, and are not effectively sparsity-aware. This work proposes the dynamic sparsity-aware mapping scheme generating method that models the problem with a sequential decision-making model, and optimizes it by reinforcement learning (RL) algorithm (REINFORCE). Our generating model (LSTM, combined with the dynamic-fill scheme) generates remarkable mapping performance on a small-scale graph/matrix data (complete mapping costs 43% area of the original matrix) and two large-scale matrix data (costing 22.5% area on qh882 and 17.1% area on qh1484). Our method may be extended to sparse graph computing on other PIM architectures, not limited to the memristive device-based platforms.

cs.LG↗

arXiv2022

Robust Adaptive Safety-Critical Control for Unknown Systems with Finite-Time Element-Wise Parameter Estimation

Safety is always one of the most critical principles for a system to be controlled. This paper investigates a safety-critical control scheme for unknown structured systems by using the control barrier function (CBF) method. Benefited from the dynamic regressor extension and mixing (DREM), an extended element-wise parameter identification law is utilized to dismiss the uncertainty. On the one hand, it is shown that the proposed control scheme can always guarantee the safety in the identification process with noised signal injection excitation, which was not considered in the previous study. On the other hand, the element-wise estimation process in DREM can minimize conservatism of the safe adaptive process compared to other existing adaptive CBF algorithms. The stability as well as the forward invariance of the presented safe control-estimation scheme is proved. Furthermore, the robustness of the scheme under bounded disturbances is analyzed, where a robust CBF with modest conditions is used to ensure safety. The framework is illustrated by simulations on adaptive cruise control, where the slope resistance of the following vehicle is robustly estimated in finite time against small disturbances and the potential crash risk is avoided by the proposed safe control scheme.

eess.SY↗

arXiv2022

Optimal Tracking Control for Unknown Linear Systems with Finite-Time Parameter Estimation

The optimal control input for linear systems can be solved from algebraic Riccati equation (ARE), from which it remains questionable to get the form of the exact solution. In engineering, the acceptable numerical solutions of ARE can be found by iteration or optimization. Recently, the gradient descent based numerical solutions has been proven effective to approximate the optimal ones. This paper introduces this method to tracking problem for heterogeneous linear systems. Differently, the parameters in the dynamics of the linear systems are all assumed to be unknown, which is intractable since the gradient as well as the allowable initialization needs the prior knowledge of system dynamics. To solve this problem, the method named dynamic regressor extension and mix (DREM) is improved to estimate the parameter matrices in finite time. Besides, a discounted factor is introduced to ensure the existence of optimal solutions for heterogeneous systems. Two simulation experiments are given to illustrate the effectiveness.

eess.SY↗