arXiv subjects

Alessandro Abate

Publications and source records attributed to Alessandro Abate.

At least 145 records · Page 8Linked to original sources

arXiv2020

Automated and Formal Synthesis of Neural Barrier Certificates for Dynamical Models

We introduce an automated, formal, counterexample-based approach to synthesise Barrier Certificates (BC) for the safety verification of continuous and hybrid dynamical models. The approach is underpinned by an inductive framework: this is structured as a sequential loop between a learner, which manipulates a candidate BC structured as a neural network, and a sound verifier, which either certifies the candidate's validity or generates counter-examples to further guide the learner. We compare the approach against state-of-the-art techniques, over polynomial and non-polynomial dynamical models: the outcomes show that we can synthesise sound BCs up to two orders of magnitude faster, with in particular a stark speedup on the verification engine (up to five orders less), whilst needing a far smaller data set (up to three orders less) for the learning part. Beyond improvements over the state of the art, we further challenge the new approach on a hybrid dynamical model and on larger-dimensional models, and showcase the numerical robustness of our algorithms and codebase.

eess.SY↗

arXiv2020

Safety Guarantees for Planning Based on Iterative Gaussian Processes

Gaussian Processes (GPs) are widely employed in control and learning because of their principled treatment of uncertainty. However, tracking uncertainty for iterative, multi-step predictions in general leads to an analytically intractable problem. While approximation methods exist, they do not come with guarantees, making it difficult to estimate their reliability and to trust their predictions. In this work, we derive formal probability error bounds for iterative prediction and planning with GPs. Building on GP properties, we bound the probability that random trajectories lie in specific regions around the predicted values. Namely, given a tolerance $ε> 0 $, we compute regions around the predicted trajectory values, such that GP trajectories are guaranteed to lie inside them with probability at least $1-ε$. We verify experimentally that our method tracks the predictive uncertainty correctly, even when current approximation techniques fail. Furthermore, we show how the proposed bounds can be employed within a safe reinforcement learning framework to verify the safety of candidate control policies, guiding the synthesis of provably safe controllers.

cs.LG↗

arXiv2020

SafePILCO: a software tool for safe and data-efficient policy synthesis

SafePILCO is a software tool for safe and data-efficient policy search with reinforcement learning. It extends the known PILCO algorithm, originally written in MATLAB, to support safe learning. We provide a Python implementation and leverage existing libraries that allow the codebase to remain short and modular, which is appropriate for wider use by the verification, reinforcement learning, and control communities.

cs.LG↗

arXiv2020

Automated and Sound Synthesis of Lyapunov Functions with SMT Solvers

In this paper we employ SMT solvers to soundly synthesise Lyapunov functions that assert the stability of a given dynamical model. The search for a Lyapunov function is framed as the satisfiability of a second-order logical formula, asking whether there exists a function satisfying a desired specification (stability) for all possible initial conditions of the model. We synthesise Lyapunov functions for linear, non-linear (polynomial), and for parametric models. For non-linear models, the algorithm also determines a region of validity for the Lyapunov function. We exploit an inductive framework to synthesise Lyapunov functions, starting from parametric templates. The inductive framework comprises two elements: a learner proposes a Lyapunov function, and a verifier checks its validity - its lack is expressed via a counterexample (a point over the state space), for further use by the learner. Whilst the verifier uses the SMT solver Z3, thus ensuring the overall soundness of the procedure, we examine two alternatives for the learner: a numerical approach based on the optimisation tool Gurobi, and a sound approach based again on Z3. The overall technique is evaluated over a broad set of benchmarks, which shows that this methodology not only scales to 10-dimensional models within reasonable computational time, but also offers a novel soundness proof for the generated Lyapunov functions and their domains of validity.

eess.SY↗

arXiv2020

Symbolic Reachability Analysis of High Dimensional Max-Plus Linear Systems

This work discusses the reachability analysis (RA) of Max-Plus Linear (MPL) systems, a class of continuous-space, discrete-event models defined over the max-plus algebra. Given the initial and target sets, we develop algorithms to verify whether there exist trajectories of the MPL system that, starting from the initial set, eventually reach the target set. We show that RA can be solved symbolically by encoding the MPL system, as well as initial and target sets into difference logic, and then checking the satisfaction of the resulting logical formula via an off-the-shelf satisfiability modulo theories (SMT) solver. The performance and scalability of the developed SMT-based algorithms are shown to clearly outperform state-of-the-art RA algorithms for MPL systems, newly allowing to investigate RA of high-dimensional MPL systems: the verification of models with more than 100 continuous variables shows the applicability of these techniques to MPL systems of industrial relevance.

cs.LO↗

arXiv2020

Computation of the Transient in Max-Plus Linear Systems via SMT-Solving

This paper proposes a new approach, grounded in Satisfiability Modulo Theories (SMT), to study the transient of a Max-Plus Linear (MPL) system, that is the number of steps leading to its periodic regime. Differently from state-of-the-art techniques, our approach allows the analysis of periodic behaviors for subsets of initial states, as well as the characterization of sets of initial states exhibiting the same specific periodic behavior and transient. Our experiments show that the proposed technique dramatically outperforms state-of-the-art methods based on max-plus algebra computations for systems of large dimensions.

eess.SY↗

arXiv2020

Temporal Logic Trees for Model Checking and Control Synthesis of Uncertain Discrete-time Systems

We propose algorithms for performing model checking and control synthesis for discrete-time uncertain systems under linear temporal logic (LTL) specifications. We construct temporal logic trees (TLT) from LTL formulae via reachability analysis. In contrast to automaton-based methods, the construction of the TLT is abstraction-free for infinite systems, that is, we do not construct discrete abstractions of the infinite systems. Moreover, for a given transition system and an LTL formula, we prove that there exist both a universal TLT and an existential TLT via minimal and maximal reachability analysis, respectively. We show that the universal TLT is an underapproximation for the LTL formula and the existential TLT is an overapproximation. We provide sufficient conditions and necessary conditions to verify whether a transition system satisfies an LTL formula by using the TLT approximations. As a major contribution of this work, for a controlled transition system and an LTL formula, we prove that a controlled TLT can be constructed from the LTL formula via control-dependent reachability analysis. Based on the controlled TLT, we design an online control synthesis algorithm, under which a set of feasible control inputs can be generated at each time step. We also prove that this algorithm is recursively feasible. We illustrate the proposed methods for both finite and infinite systems and highlight the generality and online scalability with two simulated examples.

eess.SY↗

arXiv2020

Formal Synthesis of Lyapunov Neural Networks

We propose an automatic and formally sound method for synthesising Lyapunov functions for the asymptotic stability of autonomous non-linear systems. Traditional methods are either analytical and require manual effort or are numerical but lack of formal soundness. Symbolic computational methods for Lyapunov functions, which are in between, give formal guarantees but are typically semi-automatic because they rely on the user to provide appropriate function templates. We propose a method that finds Lyapunov functions fully automatically$-$using machine learning$-$while also providing formal guarantees$-$using satisfiability modulo theories (SMT). We employ a counterexample-guided approach where a numerical learner and a symbolic verifier interact to construct provably correct Lyapunov neural networks (LNNs). The learner trains a neural network that satisfies the Lyapunov criteria for asymptotic stability over a samples set; the verifier proves via SMT solving that the criteria are satisfied over the whole domain or augments the samples set with counterexamples. Our method supports neural networks with polynomial activation functions and multiple depth and width, which display wide learning capabilities. We demonstrate our method over several non-trivial benchmarks and compare it favourably against a numerical optimisation-based approach, a symbolic template-based approach, and a cognate LNN-based approach. Our method synthesises Lyapunov functions faster and over wider spatial domains than the alternatives, yet providing stronger or equal guarantees.

eess.SY↗

arXiv2020

Bayesian Verification of Chemical Reaction Networks

We present a data-driven verification approach that determines whether or not a given chemical reaction network (CRN) satisfies a given property, expressed as a formula in a modal logic. Our approach consists of three phases, integrating formal verification over models with learning from data. First, we consider a parametric set of possible models based on a known stoichiometry and classify them against the property of interest. Secondly, we utilise Bayesian inference to update a probability distribution of the parameters within a parametric model with data gathered from the underlying CRN. In the third and final stage, we combine the results of both steps to compute the probability that the underlying CRN satisfies the given property. We apply the new approach to a case study and compare it to Bayesian statistical model checking.

cs.CE↗

arXiv2020

Cautious Reinforcement Learning with Logical Constraints

This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process. Policies are synthesised to satisfy a goal, expressed as a temporal logic formula, with maximal probability. Enforcing the RL agent to stay safe during learning might limit the exploration, however we show that the proposed architecture is able to automatically handle the trade-off between efficient progress in exploration (towards goal satisfaction) and ensuring safety. Theoretical guarantees are available on the optimality of the synthesised policies and on the convergence of the learning algorithm. Experimental results are provided to showcase the performance of the proposed method.

cs.LG↗

arXiv2019

Safe Policy Search with Gaussian Process Models

We propose a method to optimise the parameters of a policy which will be used to safely perform a given task in a data-efficient manner. We train a Gaussian process model to capture the system dynamics, based on the PILCO framework. Our model has useful analytic properties, which allow closed form computation of error gradients and estimating the probability of violating given state space constraints. During training, as well as operation, only policies that are deemed safe are implemented on the real system, minimising the risk of failure.

stat.ML↗

arXiv2019

Modular Deep Reinforcement Learning with Temporal Logic Specifications

We propose an actor-critic, model-free, and online Reinforcement Learning (RL) framework for continuous-state continuous-action Markov Decision Processes (MDPs) when the reward is highly sparse but encompasses a high-level temporal structure. We represent this temporal structure by a finite-state machine and construct an on-the-fly synchronised product with the MDP and the finite machine. The temporal structure acts as a guide for the RL agent within the product, where a modular Deep Deterministic Policy Gradient (DDPG) architecture is proposed to generate a low-level control policy. We evaluate our framework in a Mars rover experiment and we present the success rate of the synthesised policy.

cs.LG↗

arXiv2019

Verifying Reachability Properties in Markov Chains via Incremental Induction

There is a scalability gap between probabilistic and non-probabilistic verification. Probabilistic model checking tools are based either on explicit engines or on (Multi-Terminal) Binary Decision Diagrams. These structures are complemented in areas of non-probabilistic verification by more scalable techniques, such as IC3. We present a symbolic probabilistic model checking algorithm based on IC3-like incremental construction of inductive clauses to partition the state space, interleaved with incremental construction of a system of linear inequalities. This paper compares our implementation to standard quantitative verification alternatives: our experiments show that our algorithm is a step to more scalable symbolic verification of rare events in finite-state Markov chains.

cs.LO↗

arXiv2019

Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees

Reinforcement Learning (RL) has emerged as an efficient method of choice for solving complex sequential decision making problems in automatic control, computer science, economics, and biology. In this paper we present a model-free RL algorithm to synthesize control policies that maximize the probability of satisfying high-level control objectives given as Linear Temporal Logic (LTL) formulas. Uncertainty is considered in the workspace properties, the structure of the workspace, and the agent actions, giving rise to a Probabilistically-Labeled Markov Decision Process (PL-MDP) with unknown graph structure and stochastic behaviour, which is even more general case than a fully unknown MDP. We first translate the LTL specification into a Limit Deterministic Buchi Automaton (LDBA), which is then used in an on-the-fly product with the PL-MDP. Thereafter, we define a synchronous reward function based on the acceptance condition of the LDBA. Finally, we show that the RL algorithm delivers a policy that maximizes the satisfaction probability asymptotically. We provide experimental results that showcase the efficiency of the proposed method.

cs.LO↗

arXiv2019

Bounded Model Checking of Max-Plus Linear Systems via Predicate Abstractions

This paper introduces the abstraction of max-plus linear (MPL) systems via predicates. Predicates are automatically selected from system matrix, as well as from the specifications under consideration. We focus on verifying time-difference specifications, which encompass the relation between successive events in MPL systems. We implement a bounded model checking (BMC) procedure over a predicate abstraction of the given MPL system, to verify the satisfaction of time-difference specifications. Our predicate abstractions are experimentally shown to improve on existing MPL abstractions algorithms. Furthermore, with focus on the BMC algorithm, we can provide an explicit upper bound on the completeness threshold by means of the transient and the cyclicity of the underlying MPL system.

cs.LO↗

arXiv2019

Logically-Constrained Neural Fitted Q-Iteration

We propose a method for efficient training of Q-functions for continuous-state Markov Decision Processes (MDPs) such that the traces of the resulting policies satisfy a given Linear Temporal Logic (LTL) property. LTL, a modal logic, can express a wide range of time-dependent logical properties (including "safety") that are quite similar to patterns in natural language. We convert the LTL property into a limit deterministic Buchi automaton and construct an on-the-fly synchronised product MDP. The control policy is then synthesised by defining an adaptive reward function and by applying a modified neural fitted Q-iteration algorithm to the synchronised structure, assuming that no prior knowledge is available from the original MDP. The proposed method is evaluated in a numerical study to test the quality of the generated control policy and is compared with conventional methods for policy synthesis such as MDP abstraction (Voronoi quantizer) and approximate dynamic programming (fitted value iteration).

cs.LG↗

arXiv2019

Analyzing Occupancy-Driven Thermal Dynamics in Smart Buildings

The fact that a proper HVAC control strategy can reduce the energy consumption of a building by up to 45% has driven significant research in demand-based HVAC control. This paper presents a novel framework for modeling and analysis of thermal dynamics in smart buildings that incorporates building's thermal properties, a stochastic occupancy model and heating strategies. Each zone of a building is modeled with the help of discrete time Markov rewards formalism where the states represent the occupancy of that zone (either occupied or empty), and the state rewards incorporate the thermal dynamics and heating strategy. To demonstrate the applicability of our proposed framework, we evaluate and compare six different heating strategies for the two zone scenario of a university building. The obtained quantitative results from the PRISM probabilistic model checker show that one of the evaluated control strategies (viz. selective strategy) satisfies our requirement in terms of maintaining the occupants' comfort while being up to 13.5 times more cost effective when compared to the other evaluated strategies. Such evaluations demonstrate the framework's ability to assist in selecting the control strategy tailored around the occupancy pattern and building's thermal property.

eess.SY↗

arXiv2019

Logically-Constrained Reinforcement Learning

We present the first model-free Reinforcement Learning (RL) algorithm to synthesise policies for an unknown Markov Decision Process (MDP), such that a linear time property is satisfied. The given temporal property is converted into a Limit Deterministic Buchi Automaton (LDBA) and a robust reward function is defined over the state-action pairs of the MDP according to the resulting LDBA. With this reward function, the policy synthesis procedure is "constrained" by the given specification. These constraints guide the MDP exploration so as to minimize the solution time by only considering the portion of the MDP that is relevant to satisfaction of the LTL property. This improves performance and scalability of the proposed method by avoiding an exhaustive update over the whole state space while the efficiency of standard methods such as dynamic programming is hindered by excessive memory requirements, caused by the need to store a full-model in memory. Additionally, we show that the RL procedure sets up a local value iteration method to efficiently calculate the maximum probability of satisfying the given property, at any given state of the MDP. We prove that our algorithm is guaranteed to find a policy whose traces probabilistically satisfy the LTL property if such a policy exists, and additionally we show that our method produces reasonable control policies even when the LTL property cannot be satisfied. The performance of the algorithm is evaluated via a set of numerical examples. We observe an improvement of one order of magnitude in the number of iterations required for the synthesis compared to existing approaches.

cs.LG↗