STL-Based Synthesis of Feedback Controllers Using Reinforcement Learning

We consider the problem of controlling a system with unknown, stochastic dynamics to achieve a complex, time-sensitive task. An example of this problem is controlling a noisy aerial vehicle with partially known dynamics to visit a pre-specified set of regions in any order while avoiding hazardous areas. In particular, we are interested in tasks which can be described by signal temporal logic (STL) specifications. STL is a rich logic that can be used to describe tasks involving bounds on physical parameters, continuous time bounds, and logical relationships over time and states. STL is equipped with a continuous measure called the robustness degree that measures how strongly a given sample path exhibits an STL property [4, 3]. This measure enables the use of continuous optimization problems to solve learning [7, 6] or formal synthesis problems [9] involving STL.

Learning ability is the basic characteristic of human intelligence. The July 1, 2005 issue of Science published a list of 125 important questions in science. Among them, the question 94 “What are the limits of learning by machines?”. The annotation “Computers can already beat the world’s best chess players, and they have a wealth of information on the Web to draw on. But abstract reasoning is still beyond any machine”. In recent artificial intelligence has made great progresses. In 1997, the rise of the man-machine war, IBM Supercomputer Deep Blue defeated the chess master Garry Kasparov. On February 14, 2011, IBM’s Watson supercomputer won a practice round against Jeopardy champions Ken Jennings and Brad Rutter. In March 2016, Google DeepMind’s AlphaGo sealed a 4-1 victory over a South Korean Go grandmaster Lee Se-dol. This paper focuses on the machine learning methods of AlphaGo, including reinforcement learning, deep learning, deep reinforcement learning, analysis of the existing problems and the latest research progress. Deep reinforcement learning is the combination of deep learning and reinforcement learning, which can realize the learning algorithm from the perception to action. Simply said, this is the same as human behavior, input sensing information such as vision, and then, direct output action through the deep neural network. Deep reinforcement learning has the potential to learn a variety of skills for the robot to achieve full autonomy. Even though reinforcement learning is practiced successfully, but feature states need to manually set, for complex scene is a difficult thing, especially easy to cause the dimension disaster, and expression is not good. In 2010, Sascha Lange and Martin Riedmiller proposed deep auto-encoder neural networks in reinforcement learning to extract feature, which is used to control the visual correlation. In 2013, DeepMind proposed deep Q-network (DQN) in NIPS 2013, using convolution neural network to extract features, and then applied in reinforcement learning. They continue to improve and published an improved version of DQN on Nature in 2015, which has aroused widespread concern. In order to break through the limits of learning by machines, cognitive machine learning is proposed, which is the combination of machine learning and brain cognition, so that the machine intelligence is constantly evolving, and gradually reaches the human level of artificial intelligence. A cognitive model entitled Consciousness And Memory (CAM) is proposed by author, which consists of memory, consciousness, high-level cognitive functions, perception and motor. High-level cognitive functions of the brain include learning, language, thinking, decision making, emotion, and so on. Learning is a course to accept the stimulus through the nervous system and obtain new behavior, habits and accumulation experience. According to the current research progress of brain science and cognitive science, cognitive machine learning may be interested in learning emergence, procedural memory knowledge learning, learning evolution and so on. For intelligence, so-called evolution is refers to the learning of learning and the structure also follows the change. It is important to record the learning result by structure changing and improve the learning method.

Cyber-physical system applications such as autonomous vehicles, wearable devices, and avionic systems generate a large volume of time-series data. Designers often look for tools to help classify and categorize the data. Traditional machine learning techniques for time-series data offer several solutions to solve these problems; however, the artifacts trained by these algorithms often lack interpretability. On the other hand, temporal logics, such as Signal Temporal Logic (STL) have been successfully used in the formal methods community as specifications of time-series behaviors. In this work, we propose a new technique to automatically learn temporal logic formulae that are able to cluster and classify real-valued time-series data. Previous work on learning STL formulas from data either assumes a formula-template to be given by the user, or assumes some special fragment of STL that enables exploring the formula structure in a systematic fashion. In our technique, we relax these assumptions, and provide a way to systematically explore the space of all STL formulas. As the space of all STL formulas is very large, and contains many semantically equivalent formulas, we suggest a technique to heuristically prune the space of formulas considered. Finally, we illustrate our technique on various case studies from the automotive, transportation and healthcare domain.

Deep reinforcement learning (DRL) is one of the emerging areas of machine learning which focuses on maximized rewards. DRL is a type of machine learning that combines reinforcement learning and deep learning. It uses a series of algorithms to enable an agent to learn how to make decisions in a complex environment. DRL is a subset of artificial intelligence that focuses on making decisions based on the environment and the rewards associated with each action.The goal of DRL is to maximize the long-term reward of an agent. In order to do this, the agent must use a combination of deep learning, reinforcement learning and other AI techniques to learn which actions will lead to the highest reward. DRL is used to solve a variety of problems, from playing video games to controlling robots. It is also used in autonomous driving and robotics, as well as for financial trading. DRL is a powerful tool for solving complex problems and has been used in a variety of research projects. DRL has the potential to revolutionize the way we interact with machines and the environment.

Reinforcement learning is a mathematical framework for agents to interact intelligently with their environment. Unlike supervised learning, where a system learns with the help of labeled data, reinforcement learning agents learn how to act by trial and error only receiving a reward signal from their environments. A field where reinforcement learning has been prominently successful is robotics [3]. However, real-world control problems are also particularly challenging because of the noise and high- dimensionality of input data (e.g., visual input). In recent years, in the field of supervised learning, deep neural networks have been successfully used to extract meaning from this kind of data. Building on these advances, deep reinforcement learning was used to solve complex problems like Atari games and Go. Mnih et al. [1] built a system with fixed hyper parameters able to learn to play 49 different Atari games only from raw pixel inputs. However, in order to apply the same methods to real-world control problems, deep reinforcement learning has to be able to deal with continuous action spaces. Discretizing continuous action spaces would scale poorly, since the number of discrete actions grows exponentially with the dimensionality of the action. Furthermore, having a parametrized policy can be advantageous because it can generalize in the action space. Therefore with this thesis we study state-of-the-art deep reinforcement learning algorithm, Deep Deterministic Policy Gradients. We provide a theoretical comparison to other popular methods, an evaluation of its performance, identify its limitations and investigate future directions of research. The remainder of the thesis is organized as follows. We start by introducing the field of interest, machine learning, focusing our attention of deep learning and reinforcement learning. We continue by describing in details the two main algorithms, core of this study, namely Deep Q-Network (DQN) and Deep Deterministic Policy Gradients (DDPG). We then provide implementatory details of DDPG and our test environment, followed by a description of benchmark test cases. Finally, we discuss the results of our evaluation, identifying limitations of the current approach and proposing future avenues of research.

Deep Reinforcement Learning (DRL) has emerged as a transformative paradigm in the field of artificial intelligence (AI), offering unprecedented capabilities in decision-making across diverse domains. This article explores the profound impact of DRL on enhancing the decision-making capabilities of AI systems, elucidating its underlying principles, applications, and implications.DRL represents a fusion of deep learning and reinforcement learning, enabling machines to learn complex behaviors and make decisions by interacting with their environment. The utilization of neural networks allows DRL algorithms to handle high-dimensional input spaces, making it well-suited for tasks that involve intricate decision-making processes.One of the key strengths of DRL lies in its ability to address problems with sparse and delayed rewards, common challenges in traditional reinforcement learning. Through a process of trial and error, DRL algorithms can learn optimal decision strategies by navigating through a vast decision space, adapting to dynamic environments, and maximizing cumulative rewards over time.The applications of DRL span various domains, including robotics, finance, healthcare, gaming, and autonomous systems. In robotics, DRL facilitates the development of intelligent agents capable of autonomously navigating complex environments, performing intricate tasks, and adapting to unforeseen circumstances. In finance, DRL is leveraged for portfolio optimization, algorithmic trading, and risk management, demonstrating its potential to revolutionize traditional financial strategies.

A new ensemble deep graph reinforcement learning network for spatio-temporal traffic volume forecasting in a freeway network

In recent years, deep reinforcement learning (DRL) has made impressive achievements in many fields. However, existing DRL algorithms usually require a large amount of exploration to obtain a good action policy. In addition, in many complex situations, the reward function cannot be well designed to meet task requirements. These two problems will make it difficult for DRL to learn a good action policy within a relatively short period. The use of expert data can provide effective guidance and avoid unnecessary exploration. This study proposes a deep imitation reinforcement learning (DIRL) algorithm that uses a certain amount of expert demonstration data to speed up the training of DRL. In the proposed method, the learning agent imitates the expert's action policy by learning from demonstration data. After imitation learning, DRL is used to optimise the action policy in a self‐learning way. By experimental comparison on a video game called the Mario racing game, it is shown that the proposed DIRL algorithm with expert demonstration data can obtain much better performance than previous DRL algorithms without expert guidance.

Sampling-based Motion Planning with Temporal Logic Missions and Spatial Preferences

We present a general framework for risk semantics on Signal Temporal Logic (STL) specifications for stochastic dynamical systems using axiomatic risk theory. We show that under our recursive risk semantics, risk constraints on STL formulas can be expressed in terms of risk constraints on atomic predicates. We then show how this allows a (stochastic) STL risk constraint to be transformed into a risk-tightened deterministic STL constraint on a related deterministic nominal system, enabling the application of existing STL methods. For affine predicate functions and a (coherent) Distributionally Robust Value at Risk measure, we show how risk constraints on atomic predicates can be reformulated as tightened deterministic affine constraints. We demonstrate the framework using a Model Predictive Control (MPC) design with an STL risk constraint.

Design time uncertainty poses an important challenge when developing a self-adaptive system. As an example, defining how the system should adapt when facing a new environment state, requires understanding the precise effect of an adaptation, which may not be known at design time. Online reinforcement learning, i.e., employing reinforcement learning (RL) at runtime, is an emerging approach to realizing self-adaptive systems in the presence of design time uncertainty. By using Online RL, the self-adaptive system can learn from actual operational data and leverage feedback only available at runtime. Recently, Deep RL is gaining interest. Deep RL represents learned knowledge as a neural network whereby it can generalize over unseen inputs, as well as handle continuous environment states and adaptation actions. A fundamental problem of Deep RL is that learned knowledge is not explicitly represented. For a human, it is practically impossible to relate the parametrization of the neural network to concrete RL decisions and thus Deep RL essentially appears as a black box. Yet, understanding the decisions made by Deep RL is key to (1) increasing trust, and (2) facilitating debugging. Such debugging is especially relevant for self-adaptive systems, because the reward function, which quantifies the feedback to the RL algorithm, must be defined by developers. The reward function must be explicitly defined by developers, thus introducing a potential for human error. To explain Deep RL for self-adaptive systems, we enhance and combine two existing explainable RL techniques from the machine learning literature. The combined technique, XRL-DINE, overcomes the respective limitations of the individual techniques. We present a proof-of-concept implementation of XRL-DINE, as well as qualitative and quantitative results of applying XRL-DINE to a self-adaptive system exemplar.

This paper discusses an autonomous driving control strategy based on Deep Reinforcement Learning (DRL), which aims to improve the decision-making ability of autonomous driving system in complex traffic environments. Deep reinforcement learning has a wide range of applications in many fields, such as robotics and medicine. Autonomous driving has emerged as a significant research focus in recent years. By combining deep learning and reinforcement learning, the model is able to autonomously learn and optimize driving behavior under dynamically changing road conditions. The DRL-based control strategy performs well in vehicle obstacle avoidance, pedestrian recognition, and traffic rule compliance in the face of complex environments such as city streets, intersections, and congested road sections, significantly improving the safety and efficiency of autonomous driving. This article will first introduce deep reinforcement learning. Then, the autonomous driving control strategy based on deep reinforcement learning is introduced. This research provides valuable insights for developing and implementing DRL-based autonomous driving systems.

The food industry faces significant challenges in managing operational costs due to its high energy intensity and rising energy prices. Industrial food-processing facilities, with substantial thermal capacities and large demands for cooling and heating, offer promising opportunities for demand response (DR) strategies. This study explores the application of deep reinforcement learning (RL) as an innovative, data-driven approach for DR in the food industry. By leveraging the adaptive, self-learning capabilities of RL, energy costs in the investigated plant are effectively decreased. The RL algorithm was compared with the well-established optimization method Mixed Integer Linear Programming (MILP), and both were benchmarked against a reference scenario without DR. The two optimization strategies demonstrate cost savings of 17.57% and 18.65% for RL and MILP, respectively. Although RL is slightly less efficient in cost reduction, it significantly outperforms in computational speed, being approximately 20 times faster. During operation, RL only needs 2ms per optimization compared to 19s for MILP, making it a promising optimization tool for edge computing. Moreover, while MILP’s computation time increases considerably with the number of binary variables, RL efficiently learns dynamic system behavior and scales to more complex systems without significant performance degradation. These results highlight that deep RL, when applied to DR, offers substantial cost savings and computational efficiency, with broad applicability to energy management in various applications.

Path planning refers to that the mobile robot can obtain the surrounding environment information and its own state information through the sensor carried by itself, which can avoid obstacles and move towards the target point. Deep reinforcement learning consists of two parts: reinforcement learning and deep learning, mainly used to deal with perception and decision-making problems, has become an important research branch in the field of artificial intelligence. This paper first introduces the basic knowledge of deep learning and reinforcement learning. Then, the research status of deep reinforcement learning algorithm based on value function and strategy gradient in path planning is described, and the application research of deep reinforcement learning in computer game, video game and autonomous navigation is described. Finally, I made a brief summary and outlook on the algorithms and applications of deep reinforcement learning.

What is the frequency content of temporal logic formulas? That is, when we monitor a signal against a formula, which frequency bands of the signal are relevant to the logic and should be preserved, and which can be safely discarded? This question is relevant whenever signals are filtered or compressed before being monitored, which is almost always the case for analog signals. To answer this question, we focus on monitors that measure the robustness of a signal relative to a specification in Signal Temporal Logic. We prove that robustness monitors can be modeled using Volterra series. We then study the Fourier transforms of these Volterra representations, and provide a method to derive the Fourier transforms of entire formulas. We also make explicit the measurement process in temporal logic and re-define it on the basis of distributions to make it compatible with measurements in signal processing. Experiments illustrate these results. Beyond compression, this work enables the integration of temporal logic monitoring into common signal processing tool chains as just another signal processing operation, and enables a common formalism to study both logical and non-logical operations in the frequency domain, which we refer to as Logical Signal Processing.