Safe exploration is a common problem in reinforcement learning (RL) that aims to prevent agents from making disastrous decisions while exploring their environment. A family of approaches to this problem assume domain knowledge in the form of a (partial) model of this environment to decide upon the safety of an action. A so-called shield forces the RL agent to select only safe actions. However, for adoption in various applications, one must look beyond enforcing safety and also ensure the applicability of RL with good performance. We extend the applicability of shields via tight integration with state-of-the-art deep RL, and provide an extensive, empirical study in challenging, sparse-reward environments under partial observability. We show that a carefully integrated shield ensures safety and can improve the convergence rate and final performance of RL agents. We furthermore show that a shield can be used to bootstrap state-of-the-art RL agents: they remain safe after initial learning in a shielded setting, allowing us to disable a potentially too conservative shield eventually.

Controllers for dynamical systems that operate in safety-critical settings must account for stochastic disturbances. Such disturbances are often modeled as process noise in a dynamical system, and common assumptions are that the underlying distributions are known and/or Gaussian. In practice, however, these assumptions may be unrealistic and can lead to poor approximations of the true noise distribution. We present a novel controller synthesis method that does not rely on any explicit representation of the noise distributions. In particular, we address the problem of computing a controller that provides probabilistic guarantees on safely reaching a target, while also avoiding unsafe regions of the state space. First, we abstract the continuous control system into a finite-state model that captures noise by probabilistic transitions between discrete states. As a key contribution, we adapt tools from the scenario approach to compute probably approximately correct (PAC) bounds on these transition probabilities, based on a finite number of samples of the noise. We capture these bounds in the transition probability intervals of a so-called interval Markov decision process (iMDP). This iMDP is, with a user-specified confidence probability, robust against uncertainty in the transition probabilities, and the tightness of the probability intervals can be controlled through the number of samples. We use state-of-the-art verification techniques to provide guarantees on the iMDP and compute a controller for which these guarantees carry over to the original control system. In addition, we develop a tailored computational scheme that reduces the complexity of the synthesis of these guarantees on the iMDP. Benchmarks on realistic control systems show the practical applicability of our method, even when the iMDP has hundreds of millions of transitions.

We investigate the capabilities of transfer learning in the area of structural health monitoring. In particular, we are interested in damage detection for concrete structures. Typical image datasets for such problems are relatively small, calling for the transfer of learned representation from a related large-scale dataset. Past efforts of damage detection using images have mainly considered cross-domain transfer learning approaches using pre-trained ImageNet models that are subsequently fine-tuned for the target task. However, there are rising concerns about the generalizability of ImageNet representations for specific target domains, such as for visual inspection and medical imaging. We, therefore, evaluate a combination of in-domain and cross-domain transfer learning strategies for damage detection in bridges. We perform comprehensive comparisons to study the impact of cross-domain and in-domain transfer, with various initialization strategies, using six publicly available visual inspection datasets. The pre-trained models are also evaluated for their ability to cope with the extremely low-data regime. We show that the combination of cross-domain and in-domain transfer persistently shows superior performance specially with tiny datasets. Likewise, we also provide visual explanations of predictive models to enable algorithmic transparency and provide insights to experts about the intrinsic decision logic of typically black-box deep models.

Markov chain analysis is a key technique in formal verification. A practical obstacle is that all probabilities in Markov models need to be known. However, system quantities such as failure rates or packet loss ratios, etc. are often not—or only partially—known. This motivates considering parametric models with transitions labeled with functions over parameters. Whereas traditional Markov chain analysis relies on a single, fixed set of probabilities, analysing parametric Markov models focuses on synthesising parameter values that establish a given safety or performance specification $$\varphi $$φ . Examples are: what component failure rates ensure the probability of a system breakdown to be below 0.00000001?, or which failure rates maximise the performance, for instance the throughput, of the system? This paper presents various analysis algorithms for parametric discrete-time Markov chains and Markov decision processes. We focus on three problems: (a) do all parameter values within a given region satisfy $$\varphi $$φ ?, (b) which regions satisfy $$\varphi $$φ and which ones do not?, and (c) an approximate version of (b) focusing on covering a large fraction of all possible parameter values. We give a detailed account of the various algorithms, present a software tool realising these techniques, and report on an extensive experimental evaluation on benchmarks that span a wide range of applications.

Capturing uncertainty in models of complex dynamical systems is crucial to designing safe controllers. Stochastic noise causes aleatoric uncertainty, whereas imprecise knowledge of model parameters leads to epistemic uncertainty. Several approaches use formal abstractions to synthesize policies that satisfy temporal specifications related to safety and reachability. However, the underlying models exclusively capture aleatoric but not epistemic uncertainty, and thus require that model parameters are known precisely. Our contribution to overcoming this restriction is a novel abstraction-based controller synthesis method for continuous-state models with stochastic noise and uncertain parameters. By sampling techniques and robust analysis, we capture both aleatoric and epistemic uncertainty, with a user-specified confidence level, in the transition probability intervals of a so-called interval Markov decision process (iMDP). We synthesize an optimal policy on this iMDP, which translates (with the specified confidence level) to a feedback controller for the continuous model with the same performance guarantees. Our experimental benchmarks confirm that accounting for epistemic uncertainty leads to controllers that are more robust against variations in parameter values.