Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machine

We present LARL-RM (Large language model-generated Automaton for Reinforcement Learning with Reward Machine) algorithm in order to encode high-level knowledge into reinforcement learning using automaton to expedite the reinforcement learning. Our method uses Large Language Models (LLM) to obtain high-level domain-specific knowledge using prompt engineering instead of providing the reinforcement learning algorithm directly with the high-level knowledge which requires an expert to encode the automaton. We use chain-of-thought and few-shot methods for prompt engineering and demonstrate that our method works using these approaches. Additionally, LARL-RM allows for fully closed-loop reinforcement learning without the need for an expert to guide and supervise the learning since LARL-RM can use the LLM directly to generate the required high-level knowledge for the task at hand. We also show the theoretical guarantee of our algorithm to converge to an optimal policy. We demonstrate that LARL-RM speeds up the convergence by 30% by implementing our method in two case studies.

Synthesizing Efficiently Monitorable Formulas in Metric Temporal Logic

In runtime verification, manually formalizing a specification for monitoring system executions is a tedious and error-prone process. To address this issue, we consider the problem of automatically synthesizing formal specifications from system executions. To demonstrate our approach, we consider the popular specification language Metric Temporal Logic (MTL), which is particularly tailored towards specifying temporal properties for cyber-physical systems (CPS). Most of the classical approaches for synthesizing temporal logic formulas aim at minimizing the size of the formula. However, for efficiency in monitoring, along with the size, the amount of "lookahead" required for the specification becomes relevant, especially for safety-critical applications. We formalize this notion and devise a learning algorithm that synthesizes concise formulas having bounded lookahead. To do so, our algorithm reduces the synthesis task to a series of satisfiability problems in Linear Real Arithmetic (LRA) and generates MTL formulas from their satisfying assignments. The reduction uses a novel encoding of a popular MTL monitoring procedure using LRA. Finally, we implement our algorithm in a tool called TEAL and demonstrate its ability to synthesize efficiently monitorable MTL formulas in a CPS application.

Defending Our Privacy With Backdoors

The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy attacks. Unfortunately, the task of removing specific information from the models without sacrificing performance is not straightforward and has proven to be challenging. We propose a rather easy yet effective defense based on backdoor attacks to remove private information such as names of individuals from models, and focus in this work on text encoders. Specifically, through strategic insertion of backdoors, we align the embeddings of sensitive phrases with those of neutral terms-"a person" instead of the person's name. Our empirical results demonstrate the effectiveness of our backdoor-based defense on CLIP by assessing its performance using a specialized privacy attack for zero-shot classifiers. Our approach provides not only a new "dual-use" perspective on backdoor attacks, but also presents a promising avenue to enhance the privacy of individuals within models trained on uncurated web-scraped data.

Reinforcement Learning with Temporal-Logic-Based Causal Diagrams

We study a class of reinforcement learning (RL) tasks where the objective of the agent is to accomplish temporally extended goals. In this setting, a common approach is to represent the tasks as deterministic finite automata (DFA) and integrate them into the state-space for RL algorithms. However, while these machines model the reward function, they often overlook the causal knowledge about the environment. To address this limitation, we propose the Temporal-Logic-based Causal Diagram (TL-CD) in RL, which captures the temporal causal relationships between different properties of the environment. We exploit the TL-CD to devise an RL algorithm in which an agent requires significantly less exploration of the environment. To this end, based on a TL-CD and a task DFA, we identify configurations where the agent can determine the expected rewards early during an exploration. Through a series of case studies, we demonstrate the benefits of using TL-CDs, particularly the faster convergence of the algorithm to an optimal policy due to reduced exploration of the environment.

Interpretable Anomaly Detection via Discrete Optimization

Anomaly detection is essential in many application domains, such as cyber security, law enforcement, medicine, and fraud protection. However, the decision-making of current deep learning approaches is notoriously hard to understand, which often limits their practical applicability. To overcome this limitation, we propose a framework for learning inherently interpretable anomaly detectors from sequential data. More specifically, we consider the task of learning a deterministic finite automaton (DFA) from a given multi-set of unlabeled sequences. We show that this problem is computationally hard and develop two learning algorithms based on constraint optimization. Moreover, we introduce novel regularization schemes for our optimization problems that improve the overall interpretability of our DFAs. Using a prototype implementation, we demonstrate that our approach shows promising results in terms of accuracy and F1 score.

Deep Anomaly Detection on Tennessee Eastman Process Data

This paper provides the first comprehensive evaluation and analysis of modern (deep-learning) unsupervised anomaly detection methods for chemical process data. We focus on the Tennessee Eastman process dataset, which has been a standard litmus test to benchmark anomaly detection methods for nearly three decades. Our extensive study will facilitate choosing appropriate anomaly detection methods in industrial applications.

Learning Temporal Logic Properties: an Overview of Two Recent Methods

Learning linear temporal logic (LTL) formulas from examples labeled as positive or negative has found applications in inferring descriptions of system behavior. We summarize two methods to learn LTL formulas from examples in two different problem settings. The first method assumes noise in the labeling of the examples. For that, they define the problem of inferring an LTL formula that must be consistent with most but not all of the examples. The second method considers the other problem of inferring meaningful LTL formulas in the case where only positive examples are given. Hence, the first method addresses the robustness to noise, and the second method addresses the balance between conciseness and specificity (i.e., language minimality) of the inferred formula. The summarized methods propose different algorithms to solve the aforementioned problems, as well as to infer other descriptions of temporal properties, such as signal temporal logic or deterministic finite automata.

Analyzing Robustness of Angluin's L* Algorithm in Presence of Noise

Angluin's L* algorithm learns the minimal (complete) deterministic finite automaton (DFA) of a regular language using membership and equivalence queries. Its probabilistic approximatively correct (PAC) version substitutes an equivalence query by a large enough set of random membership queries to get a high level confidence to the answer. Thus it can be applied to any kind of (also non-regular) device and may be viewed as an algorithm for synthesizing an automaton abstracting the behavior of the device based on observations. Here we are interested on how Angluin's PAC learning algorithm behaves for devices which are obtained from a DFA by introducing some noise. More precisely we study whether Angluin's algorithm reduces the noise and produces a DFA closer to the original one than the noisy device. We propose several ways to introduce the noise: (1) the noisy device inverts the classification of words w.r.t. the DFA with a small probability, (2) the noisy device modifies with a small probability the letters of the word before asking its classification w.r.t. the DFA, and (3) the noisy device combines the classification of a word w.r.t. the DFA and its classification w.r.t. a counter automaton. Our experiments were performed on several hundred DFAs. Our main contributions, bluntly stated, consist in showing that: (1) Angluin's algorithm behaves well whenever the noisy device is produced by a random process, (2) but poorly with a structured noise, and, that (3) almost surely randomness yields systems with non-recursively enumerable languages.

Learning Interpretable Temporal Properties from Positive Examples Only

We consider the problem of explaining the temporal behavior of black-box systems using human-interpretable models. To this end, based on recent research trends, we rely on the fundamental yet interpretable models of deterministic finite automata (DFAs) and linear temporal logic (LTL) formulas. In contrast to most existing works for learning DFAs and LTL formulas, we rely on only positive examples. Our motivation is that negative examples are generally difficult to observe, in particular, from black-box systems. To learn meaningful models from positive examples only, we design algorithms that rely on conciseness and language minimality of models as regularizers. To this end, our algorithms adopt two approaches: a symbolic and a counterexample-guided one. While the symbolic approach exploits an efficient encoding of language minimality as a constraint satisfaction problem, the counterexample-guided one relies on generating suitable negative examples to prune the search. Both the approaches provide us with effective algorithms with theoretical guarantees on the learned models. To assess the effectiveness of our algorithms, we evaluate all of them on synthetic data.

Specification sketching for Linear Temporal Logic

Virtually all verification and synthesis techniques assume that the formal specifications are readily available, functionally correct, and fully match the engineer's understanding of the given system. However, this assumption is often unrealistic in practice: formalizing system requirements is notoriously difficult, error-prone, and requires substantial training. To alleviate this severe hurdle, we propose a fundamentally novel approach to writing formal specifications, named specification sketching for Linear Temporal Logic (LTL). The key idea is that an engineer can provide a partial LTL formula, called an LTL sketch, where parts that are hard to formalize can be left out. Given a set of examples describing system behaviors that the specification should or should not allow, the task of a so-called sketching algorithm is then to complete a given sketch such that the resulting LTL formula is consistent with the examples. We show that deciding whether a sketch can be completed falls into the complexity class NP and present two SAT-based sketching algorithms. We also demonstrate that sketching is a practical approach to writing formal specifications using a prototype implementation.