arXiv subjects

Rajeev Alur

Publications and source records attributed to Rajeev Alur.

At least 37 records · Page 2Linked to original sources

arXiv2023

Stability Guarantees for Feature Attributions with Multiplicative Smoothing

Explanation methods for machine learning models tend not to provide any formal guarantees and may not reflect the underlying decision-making process. In this work, we analyze stability as a property for reliable feature attribution methods. We prove that relaxed variants of stability are guaranteed if the model is sufficiently Lipschitz with respect to the masking of features. We develop a smoothing method called Multiplicative Smoothing (MuS) to achieve such a model. We show that MuS overcomes the theoretical limitations of standard smoothing techniques and can be integrated with any classifier and feature attribution method. We evaluate MuS on vision and language models with various feature attribution methods, such as LIME and SHAP, and demonstrate that MuS endows feature attributions with non-trivial stability guarantees.

cs.LG↗

arXiv2023

Robust Subtask Learning for Compositional Generalization

Compositional reinforcement learning is a promising approach for training policies to perform complex long-horizon tasks. Typically, a high-level task is decomposed into a sequence of subtasks and a separate policy is trained to perform each subtask. In this paper, we focus on the problem of training subtask policies in a way that they can be used to perform any task; here, a task is given by a sequence of subtasks. We aim to maximize the worst-case performance over all tasks as opposed to the average-case performance. We formulate the problem as a two agent zero-sum game in which the adversary picks the sequence of subtasks. We propose two RL algorithms to solve this game: one is an adaptation of existing multi-agent RL algorithms to our setting and the other is an asynchronous version which enables parallel training of subtask policies. We evaluate our approach on two multi-task environments with continuous states and actions and demonstrate that our algorithms outperform state-of-the-art baselines.

cs.LG↗

arXiv2023

Policy Synthesis and Reinforcement Learning for Discounted LTL

The difficulty of manually specifying reward functions has led to an interest in using linear temporal logic (LTL) to express objectives for reinforcement learning (RL). However, LTL has the downside that it is sensitive to small perturbations in the transition probabilities, which prevents probably approximately correct (PAC) learning without additional assumptions. Time discounting provides a way of removing this sensitivity, while retaining the high expressivity of the logic. We study the use of discounted LTL for policy synthesis in Markov decision processes with unknown transition probabilities, and show how to reduce discounted LTL to discounted-sum reward via a reward machine when all discount factors are identical.

cs.LO↗

arXiv2022

Specification-Guided Learning of Nash Equilibria with High Social Welfare

Reinforcement learning has been shown to be an effective strategy for automatically training policies for challenging control problems. Focusing on non-cooperative multi-agent systems, we propose a novel reinforcement learning framework for training joint policies that form a Nash equilibrium. In our approach, rather than providing low-level reward functions, the user provides high-level specifications that encode the objective of each agent. Then, guided by the structure of the specifications, our algorithm searches over policies to identify one that provably forms an $ε$-Nash equilibrium (with high probability). Importantly, it prioritizes policies in a way that maximizes social welfare across all agents. Our empirical evaluation demonstrates that our algorithm computes equilibrium policies with high social welfare, whereas state-of-the-art baselines either fail to compute Nash equilibria or compute ones with comparatively lower social welfare.

cs.GT↗

arXiv2022

A Framework for Transforming Specifications in Reinforcement Learning

Reactive synthesis algorithms allow automatic construction of policies to control an environment modeled as a Markov Decision Process (MDP) that are optimal with respect to high-level temporal logic specifications. However, they assume that the MDP model is known a priori. Reinforcement Learning (RL) algorithms, in contrast, are designed to learn an optimal policy when the transition probabilities of the MDP are unknown, but require the user to associate local rewards with transitions. The appeal of high-level temporal logic specifications has motivated research to develop RL algorithms for synthesis of policies from specifications. To understand the techniques, and nuanced variations in their theoretical guarantees, in the growing body of resulting literature, we develop a formal framework for defining transformations among RL tasks with different forms of objectives. We define the notion of a sampling-based reduction to transform a given MDP into another one which can be simulated even when the transition probabilities of the original MDP are unknown. We formalize the notions of preservation of optimal policies, convergence, and robustness of such reductions. We then use our framework to restate known results, establish new results to fill in some gaps, and identify open problems. In particular, we show that certain kinds of reductions from LTL specifications to reward-based ones do not exist, and prove the non-existence of RL algorithms with PAC-MDP guarantees for safety specifications.

cs.FL↗

arXiv2022

Stream Processing With Dependency-Guided Synchronization (Extended Version)

Real-time data processing applications with low latency requirements have led to the increasing popularity of stream processing systems. While such systems offer convenient APIs that can be used to achieve data parallelism automatically, they offer limited support for computations that require synchronization between parallel nodes. In this paper, we propose *dependency-guided synchronization (DGS)*, an alternative programming model for stateful streaming computations with complex synchronization requirements. In the proposed model, the input is viewed as partially ordered, and the program consists of a set of parallelization constructs which are applied to decompose the partial order and process events independently. Our programming model maps to an execution model called *synchronization plans* which supports synchronization between parallel nodes. Our evaluation shows that APIs offered by two widely used systems -- Flink and Timely Dataflow -- cannot suitably expose parallelism in some representative applications. In contrast, DGS enables implementations with scalable performance, the resulting synchronization plans offer throughput improvements when implemented manually in existing systems, and the programming overhead is small compared to writing sequential code.

cs.PL↗

arXiv2021

Compositional Reinforcement Learning from Logical Specifications

We study the problem of learning control policies for complex tasks given by logical specifications. Recent approaches automatically generate a reward function from a given specification and use a suitable reinforcement learning algorithm to learn a policy that maximizes the expected reward. These approaches, however, scale poorly to complex tasks that require high-level planning. In this work, we develop a compositional learning approach, called DiRL, that interleaves high-level planning and reinforcement learning. First, DiRL encodes the specification as an abstract graph; intuitively, vertices and edges of the graph correspond to regions of the state space and simpler sub-tasks, respectively. Our approach then incorporates reinforcement learning to learn neural network policies for each edge (sub-task) within a Dijkstra-style planning algorithm to compute a high-level plan in the graph. An evaluation of the proposed approach on a set of challenging control benchmarks with continuous state and action spaces demonstrates that it outperforms state-of-the-art baselines.

cs.LG↗

arXiv2021

NetRep: Automatic Repair for Network Programs

Debugging imperative network programs is a challenging task for developers because understanding various network modules and complicated data structures is typically time-consuming. To address the challenge, this paper presents an automated technique for repairing network programs from unit tests. Specifically, given as input a faulty network program and a set of unit tests, our approach localizes the fault through symbolic reasoning, and synthesizes a patch such that the repaired program can pass all unit tests. It applies domain-specific abstraction to simplify network data structures and utilizes modular analysis to facilitate function summary reuse for symbolic analysis. We implement the proposed techniques in a tool called NetRep and evaluate it on 10 benchmarks adapted from real-world software-defined networking controllers. The evaluation results demonstrate the effectiveness and efficiency of NetRep for repairing network programs.

cs.SE↗

arXiv2021

Abstract Value Iteration for Hierarchical Reinforcement Learning

We propose a novel hierarchical reinforcement learning framework for control with continuous state and action spaces. In our framework, the user specifies subgoal regions which are subsets of states; then, we (i) learn options that serve as transitions between these subgoal regions, and (ii) construct a high-level plan in the resulting abstract decision process (ADP). A key challenge is that the ADP may not be Markov, which we address by proposing two algorithms for planning in the ADP. Our first algorithm is conservative, allowing us to prove theoretical guarantees on its performance, which help inform the design of subgoal regions. Our second algorithm is a practical one that interweaves planning at the abstract level and learning at the concrete level. In our experiments, we demonstrate that our approach outperforms state-of-the-art hierarchical reinforcement learning algorithms on several challenging benchmarks.

cs.LG↗

arXiv2020

A Composable Specification Language for Reinforcement Learning Tasks

Reinforcement learning is a promising approach for learning control policies for robot tasks. However, specifying complex tasks (e.g., with multiple objectives and safety constraints) can be challenging, since the user must design a reward function that encodes the entire task. Furthermore, the user often needs to manually shape the reward to ensure convergence of the learning algorithm. We propose a language for specifying complex control tasks, along with an algorithm that compiles specifications in our language into a reward function and automatically performs reward shaping. We implement our approach in a tool called SPECTRL, and show that it outperforms several state-of-the-art baselines.

cs.LG↗

arXiv2020

Session-layer Attack Traffic Classification by Program Synthesis

Writing classification rules to identify malicious network traffic is a time-consuming and error-prone task. Learning-based classification systems automatically extract such rules from positive and negative traffic examples. However, due to limitations in the representation of network traffic and the learning strategy, these systems lack both expressiveness to cover a range of attacks and interpretability in fully describing the attack traffic's structure at the session layer. This paper presents Sharingan system, which uses program synthesis techniques to generate network classification programs at the session layer. Sharingan accepts raw network traces as inputs, and reports potential patterns of the attack traffic in NetQRE, a domain specific language designed for specifying session-layer quantitative properties. Using Sharingan, network operators can better analyze the attack pattern due to the following advantages of Sharingan's learning process: (1) it requires minimal feature engineering, (2) it is amenable to efficient implementation of the learnt classifier, and (3) the synthesized program is easy to decipher and edit. We develop a range of novel optimizations that reduce the synthesis time for large and complex tasks to a matter of minutes. Our experiments show that Sharingan is able to correctly identify attacks from a diverse set of network attack traces and generates explainable outputs, while achieving accuracy comparable to state-of-the-art learning-based intrusion detection systems.

cs.PL↗

arXiv2020

Computer-Aided Personalized Education

The shortage of people trained in STEM fields is becoming acute, and universities and colleges are straining to satisfy this demand. In the case of computer science, for instance, the number of US students taking introductory courses has grown three-fold in the past decade. Recently, massive open online courses (MOOCs) have been promoted as a way to ease this strain. This at best provides access to education. The bigger challenge though is coping with heterogeneous backgrounds of different students, retention, providing feedback, and assessment. Personalized education relying on computational tools can address this challenge. While automated tutoring has been studied at different times in different communities, recent advances in computing and education technology offer exciting opportunities to transform the manner in which students learn. In particular, at least three trends are significant. First, progress in logical reasoning, data analytics, and natural language processing has led to tutoring tools for automatic assessment, personalized instruction including targeted feedback, and adaptive content generation for a variety of subjects. Second, research in the science of learning and human-computer interaction is leading to a better understanding of how different students learn, when and what types of interventions are effective for different instructional goals, and how to measure the success of educational tools. Finally, the recent emergence of online education platforms, both in academia and industry, is leading to new opportunities for the development of a shared infrastructure. This CCC workshop brought together researchers developing educational tools based on technologies such as logical reasoning and machine learning with researchers in education, human-computer interaction, and cognitive psychology.

cs.CY↗

arXiv2019

Streamable Regular Transductions

Motivated by real-time monitoring and data processing applications, we develop a formal theory of quantitative queries for streaming data that can be evaluated efficiently. We consider the model of unambiguous Cost Register Automata (CRAs), which are machines that combine finite-state control (for identifying regular patterns) with a finite set of data registers (for computing numerical aggregates). The definition of CRAs is parameterized by the collection of numerical operations that can be applied to the registers. These machines give rise to the class of streamable regular transductions (SR), and to the class of streamable linear regular transductions (SLR) when the register updates are copyless, i.e. every register appears at most once the right-hand-side expressions of the updates. We give a logical characterization of the class SR (resp., SLR) using MSO-definable transformations from strings to DAGs (resp., trees) without backward edges. Additionally, we establish that the two classes SR and SLR are closed under operations that are relevant for designing query languages. Finally, we study the relationship with weighted automata (WA), and show that CRAs over a suitably chosen set of operations correspond to WA, thus establishing that WA are a special case of CRAs.

cs.FL↗

arXiv2019

Case Study: Verifying the Safety of an Autonomous Racing Car with a Neural Network Controller

This paper describes a verification case study on an autonomous racing car with a neural network (NN) controller. Although several verification approaches have been proposed over the last year, they have only been evaluated on low-dimensional systems or systems with constrained environments. To explore the limits of existing approaches, we present a challenging benchmark in which the NN takes raw LiDAR measurements as input and outputs steering for the car. We train a dozen NNs using two reinforcement learning algorithms and show that the state of the art in verification can handle systems with around 40 LiDAR rays, well short of a typical LiDAR scan with 1081 rays. Furthermore, we perform real experiments to investigate the benefits and limitations of verification with respect to the sim2real gap, i.e., the difference between a system's modeled and real performance. We identify cases, similar to the modeled environment, in which verification is strongly correlated with safe behavior. Finally, we illustrate LiDAR fault patterns that can be used to develop robust and safe reinforcement learning algorithms.

eess.SY↗

arXiv2019

SyGuS-Comp 2018: Results and Analysis

Syntax-guided synthesis (SyGuS) is the computational problem of finding an implementation $f$ that meets both a semantic constraint given by a logical formula $ϕ$ in a background theory $\mathbb{T}$, and a syntactic constraint given by a grammar $G$, which specifies the allowed set of candidate implementations. Such a synthesis problem can be formally defined in the SyGuS input format (SyGuS-IF), a language that is built on top of SMT-LIB. The Syntax-Guided Synthesis competition (SyGuS-Comp) is an effort to facilitate, bring together and accelerate research and development of efficient solvers for SyGuS by providing a platform for evaluating different synthesis techniques on a comprehensive set of benchmarks. In the 5th SyGuS-Comp, five solvers competed on over 1600 benchmarks across various tracks. This paper presents and analyses the results of this year's (2018) SyGuS competition.

cs.PL↗

arXiv2019

REAFFIRM: Model-Based Repair of Hybrid Systems for Improving Resiliency

Model-based design offers a promising approach for assisting developers to build reliable and secure cyber-physical systems (CPSs) in a systematic manner. In this methodology, a designer first constructs a model, with mathematically precise semantics, of the system under design, and performs extensive analysis with respect to correctness requirements before generating the implementation from the model. However, as new vulnerabilities are discovered, requirements evolve aimed at ensuring resiliency. There is currently a shortage of an inexpensive, automated mechanism that can effectively repair the initial design, and a model-based system developer regularly needs to redesign and reimplement the system from scratch. In this paper, we propose a new methodology along with a Matlab toolkit called REAFFIRM to facilitate the model-based repair for improving the resiliency of CPSs. REAFFIRM takes the inputs including 1) an original hybrid system modeled as a Simulink/Stateflow diagram, 2) a given resiliency pattern specified as a model transformation script, and 3) a safety requirement expressed as a Signal Temporal Logic formula, and then outputs a repaired model which satisfies the requirement. The overall structure of REAFFIRM contains two main modules, a model transformation, and a model synthesizer built on top of the falsification tool Breach. We introduce a new model transformation language for hybrid systems, which we call HATL to allow a designer to specify resiliency patterns. To evaluate the proposed approach, we use REAFFIRM to automatically synthesize repaired models for an adaptive cruise control (ACC) system under a GPS sensor spoofing attack, for a single-machine infinite-bus (SMIB) system under a sliding-mode switching attack, and for a missile guidance system under gyroscopes sensor attack.

eess.SY↗

arXiv2018

Verisig: verifying safety properties of hybrid systems with neural network controllers

This paper presents Verisig, a hybrid system approach to verifying safety properties of closed-loop systems using neural networks as controllers. Although techniques exist for verifying input/output properties of the neural network itself, these methods cannot be used to verify properties of the closed-loop system (since they work with piecewise-linear constraints that do not capture non-linear plant dynamics). To overcome this challenge, we focus on sigmoid-based networks and exploit the fact that the sigmoid is the solution to a quadratic differential equation, which allows us to transform the neural network into an equivalent hybrid system. By composing the network's hybrid system with the plant's, we transform the problem into a hybrid system verification problem which can be solved using state-of-the-art reachability tools. We show that reachability is decidable for networks with one hidden layer and decidable for general networks if Schanuel's conjecture is true. We evaluate the applicability and scalability of Verisig in two case studies, one from reinforcement learning and one in which the neural network is used to approximate a model predictive controller.

eess.SY↗

arXiv2018

Equilibria in Quantitative Concurrent Games

Synthesis of finite-state controllers from high-level specifications in multi-agent systems can be reduced to solving multi-player concurrent games over finite graphs. The complexity of solving such games with qualitative objectives for agents, such as reaching a target set, is well understood resulting in tools with applications in robotics. In this paper, we introduce quantitative concurrent graph games, where transitions have separate costs for different agents, and each agent attempts to reach its target set while minimizing its own cost along the path. In this model, a solution to the game corresponds to a set of strategies, one per agent, that forms a Nash equilibrium. We study the problem of computing the set of all Pareto-optimal Nash equilibria, and give a comprehensive analysis of its complexity and related problems such as the price of stability and the price of anarchy. In particular, while checking the existence of a Nash equilibrium is NP-complete in general, with multiple parameters contributing to the computational hardness separately, two-player games with bounded costs on individual transitions admit a polynomial-time solution.

cs.GT↗