Towards Causal Temporal Reasoning for Markov Decision Processes

We introduce a new probabilistic temporal logic for the verification of Markov Decision Processes (MDP). Our logic is the first to include operators for causal reasoning, allowing us to express interventional and counterfactual queries. Given a path formula $\phi$, an interventional property is concerned with the satisfaction probability of $\phi$ if we apply a particular change $I$ to the MDP (e.g., switching to a different policy); a counterfactual allows us to compute, given an observed MDP path $\tau$, what the outcome of $\phi$ would have been had we applied $I$ in the past. For its ability to reason about different configurations of the MDP, our approach represents a departure from existing probabilistic temporal logics that can only reason about a fixed system configuration. From a syntactic viewpoint, we introduce a generalized counterfactual operator that subsumes both interventional and counterfactual probabilities as well as the traditional probabilistic operator found in e.g., PCTL. From a semantics viewpoint, our logic is interpreted over a structural causal model (SCM) translation of the MDP, which gives us a representation amenable to counterfactual reasoning. We provide a proof-of-concept evaluation of our logic on a reach-avoid task in a grid-world model.

Conformal Quantitative Predictive Monitoring of STL Requirements for Stochastic Processes

We consider the problem of predictive monitoring (PM), i.e., predicting at runtime the satisfaction of a desired property from the current system's state. Due to its relevance for runtime safety assurance and online control, PM methods need to be efficient to enable timely interventions against predicted violations, while providing correctness guarantees. We introduce \textit{quantitative predictive monitoring (QPM)}, the first PM method to support stochastic processes and rich specifications given in Signal Temporal Logic (STL). Unlike most of the existing PM techniques that predict whether or not some property $\phi$ is satisfied, QPM provides a quantitative measure of satisfaction by predicting the quantitative (aka robust) STL semantics of $\phi$. QPM derives prediction intervals that are highly efficient to compute and with probabilistic guarantees, in that the intervals cover with arbitrary probability the STL robustness values relative to the stochastic evolution of the system. To do so, we take a machine-learning approach and leverage recent advances in conformal inference for quantile regression, thereby avoiding expensive Monte-Carlo simulations at runtime to estimate the intervals. We also show how our monitors can be combined in a compositional manner to handle composite formulas, without retraining the predictors nor sacrificing the guarantees. We demonstrate the effectiveness and scalability of QPM over a benchmark of four discrete-time stochastic processes with varying degrees of complexity.

Neural Predictive Monitoring under Partial Observability

We consider the problem of predictive monitoring (PM), i.e., predicting at runtime future violations of a system from the current state. We work under the most realistic settings where only partial and noisy observations of the state are available at runtime. Such settings directly affect the accuracy and reliability of the reachability predictions, jeopardizing the safety of the system. In this work, we present a learning-based method for PM that produces accurate and reliable reachability predictions despite partial observability (PO). We build on Neural Predictive Monitoring (NPM), a PM method that uses deep neural networks for approximating hybrid systems reachability, and extend it to the PO case. We propose and compare two solutions, an end-to-end approach, which directly operates on the rough observations, and a two-step approach, which introduces an intermediate state estimation step. Both solutions rely on conformal prediction to provide 1) probabilistic guarantees in the form of prediction regions and 2) sound estimates of predictive uncertainty. We use the latter to identify unreliable (and likely erroneous) predictions and to retrain and improve the monitors on these uncertain inputs (i.e., active learning). Our method results in highly accurate reachability predictions and error detection, as well as tight prediction regions with guaranteed coverage.

Certification of Iterative Predictions in Bayesian Neural Networks

We consider the problem of computing reach-avoid probabilities for iterative predictions made with Bayesian neural network (BNN) models. Specifically, we leverage bound propagation techniques and backward recursion to compute lower bounds for the probability that trajectories of the BNN model reach a given set of states while avoiding a set of unsafe states. We use the lower bounds in the context of control and reinforcement learning to provide safety certification for given control policies, as well as to synthesize control policies that improve the certification bounds. On a set of benchmarks, we demonstrate that our framework can be employed to certify policies over BNNs predictions for problems of more than $10$ dimensions, and to effectively synthesize policies that significantly increase the lower bound on the satisfaction probability.

On Guaranteed Optimal Robust Explanations for NLP Models

We build on abduction-based explanations for ma-chine learning and develop a method for computing local explanations for neural network models in natural language processing (NLP). Our explanations comprise a subset of the words of the in-put text that satisfies two key features: optimality w.r.t. a user-defined cost function, such as the length of explanation, and robustness, in that they ensure prediction invariance for any bounded perturbation in the embedding space of the left out words. We present two solution algorithms, respectively based on implicit hitting sets and maximum universal subsets, introducing a number of algorithmic improvements to speed up convergence of hard instances. We show how our method can be con-figured with different perturbation sets in the em-bedded space and used to detect bias in predictions by enforcing include/exclude constraints on biased terms, as well as to enhance existing heuristic-based NLP explanation frameworks such as Anchors. We evaluate our framework on three widely used sentiment analysis tasks and texts of up to100words from SST, Twitter and IMDB datasets,demonstrating the effectiveness of the derived explanations.

Learnable Strategies for Bilateral Agent Negotiation over Multiple Issues

We present a novel bilateral negotiation model that allows a self-interested agent to learn how to negotiate over multiple issues in the presence of user preference uncertainty. The model relies upon interpretable strategy templates representing the tactics the agent should employ during the negotiation and learns template parameters to maximize the average utility received over multiple negotiations, thus resulting in optimal bid acceptance and generation. Our model also uses deep reinforcement learning to evaluate threshold utility values, for those tactics that require them, thereby deriving optimal utilities for every environment state. To handle user preference uncertainty, the model relies on a stochastic search to find user model that best agrees with a given partial preference profile. Multi-objective optimization and multi-criteria decision-making methods are applied at negotiation time to generate Pareto-optimal outcomes thereby increasing the number of successful (win-win) negotiations. Rigorous experimental evaluations show that the agent employing our model outperforms the winning agents of the 10th Automated Negotiating Agents Competition (ANAC'19) in terms of individual as well as social-welfare utilities.

MPC-guided Imitation Learning of Neural Network Policies for the Artificial Pancreas

Even though model predictive control (MPC) is currently the main algorithm for insulin control in the artificial pancreas (AP), it usually requires complex online optimizations, which are infeasible for resource-constrained medical devices. MPC also typically relies on state estimation, an error-prone process. In this paper, we introduce a novel approach to AP control that uses Imitation Learning to synthesize neural-network insulin policies from MPC-computed demonstrations. Such policies are computationally efficient and, by instrumenting MPC at training time with full state information, they can directly map measurements into optimal therapy decisions, thus bypassing state estimation. We apply Bayesian inference via Monte Carlo Dropout to learn policies, which allows us to quantify prediction uncertainty and thereby derive safer therapy decisions. We show that our control policies trained under a specific patient model readily generalize (in terms of model parameters and disturbance distributions) to patient cohorts, consistently outperforming traditional MPC with state estimation.

A Deep Reinforcement Learning Approach to Concurrent Bilateral Negotiation

We present a novel negotiation model that allows an agent to learn how to negotiate during concurrent bilateral negotiations in unknown and dynamic e-markets. The agent uses an actor-critic architecture with model-free reinforcement learning to learn a strategy expressed as a deep neural network. We pre-train the strategy by supervision from synthetic market data, thereby decreasing the exploration time required for learning during negotiation. As a result, we can build automated agents for concurrent negotiations that can adapt to different e-market settings without the need to be pre-programmed. Our experimental evaluation shows that our deep reinforcement learning-based agents outperform two existing well-known negotiation strategies in one-to-many concurrent bilateral negotiations for a range of e-market settings.

Neural Simplex Architecture

We present the Neural Simplex Architecture (NSA), a new approach to runtime assurance that provides safety guarantees for neural controllers (obtained e.g. using reinforcement learning) of complex autonomous and other cyber-physical systems without unduly sacrificing performance. NSA is inspired by the Simplex control architecture of Sha et al., but with some significant differences. In the traditional Simplex approach, the advanced controller (AC) is treated as a black box; there are no techniques for correcting the AC after it generates a potentially unsafe control input that causes a failover to the BC. Our NSA addresses this limitation. NSA not only provides safety assurances for CPSs in the presence of a possibly faulty neural controller, but can also improve the safety of such a controller in an online setting via retraining, without degrading its performance. NSA also offers reverse switching strategies, which allow the AC to resume control of the system under reasonable conditions, allowing the mission to continue unabated. Our experimental results on several significant case studies, including a target-seeking ground rover navigating an obstacle field and a neural controller for an artificial pancreas system, demonstrate NSA's benefits.

Statistical Guarantees for the Robustness of Bayesian Neural Networks

We introduce a probabilistic robustness measure for Bayesian Neural Networks (BNNs), defined as the probability that, given a test point, there exists a point within a bounded set such that the BNN prediction differs between the two. Such a measure can be used, for instance, to quantify the probability of the existence of adversarial examples. Building on statistical verification techniques for probabilistic models, we develop a framework that allows us to estimate probabilistic robustness for a BNN with statistical guarantees, i.e., with a priori error and confidence bounds. We provide experimental comparison for several approximate BNN inference techniques on image classification tasks associated to MNIST and a two-class subset of the GTSRB dataset. Our results enable quantification of uncertainty of BNN predictions in adversarial settings.