Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Preface 1. Decision-Theoretic Foundations 1.1 Game Theory, Rationality, and Intelligence 1.2 Basic Concepts of Decision Theory 1.3 Axioms 1.4 The Expected-Utility Maximization Theorem 1.5 Equivalent Representations 1.6 Bayesian Conditional-Probability Systems 1.7 Limitations of the Bayesian Model 1.8 Domination 1.9 Proofs of the Domination Theorems Exercises 2. Basic Models 2.1 Games in Extensive Form 2.2 Strategic Form and the Normal Representation 2.3 Equivalence of Strategic-Form Games 2.4 Reduced Normal Representations 2.5 Elimination of Dominated Strategies 2.6 Multiagent Representations 2.7 Common Knowledge 2.8 Bayesian Games 2.9 Modeling Games with Incomplete Information Exercises 3. Equilibria of Strategic-Form Games 3.1 Domination and Ratonalizability 3.2 Nash Equilibrium 3.3 Computing Nash Equilibria 3.4 Significance of Nash Equilibria 3.5 The Focal-Point Effect 3.6 The Decision-Analytic Approach to Games 3.7 Evolution. Resistance. and Risk Dominance 3.8 Two-Person Zero-Sum Games 3.9 Bayesian Equilibria 3.10 Purification of Randomized Strategies in Equilibria 3.11 Auctions 3.12 Proof of Existence of Equilibrium 3.13 Infinite Strategy Sets Exercises 4. Sequential Equilibria of Extensive-Form Games 4.1 Mixed Strategies and Behavioral Strategies 4.2 Equilibria in Behavioral Strategies 4.3 Sequential Rationality at Information States with Positive Probability 4.4 Consistent Beliefs and Sequential Rationality at All Information States 4.5 Computing Sequential Equilibria 4.6 Subgame-Perfect Equilibria 4.7 Games with Perfect Information 4.8 Adding Chance Events with Small Probability 4.9 Forward Induction 4.10 Voting and Binary Agendas 4.11 Technical Proofs Exercises 5. Refinements of Equilibrium in Strategic Form 5.1 Introduction 5.2 Perfect Equilibria 5.3 Existence of Perfect and Sequential Equilibria 5.4 Proper Equilibria 5.5 Persistent Equilibria 5.6 Stable Sets 01 Equilibria 5.7 Generic Properties 5.8 Conclusions Exercises 6. Games with Communication 6.1 Contracts and Correlated Strategies 6.2 Correlated Equilibria 6.3 Bayesian Games with Communication 6.4 Bayesian Collective-Choice Problems and Bayesian Bargaining Problems 6.5 Trading Problems with Linear Utility 6.6 General Participation Constraints for Bayesian Games with Contracts 6.7 Sender-Receiver Games 6.8 Acceptable and Predominant Correlated Equilibria 6.9 Communication in Extensive-Form and Multistage Games Exercises Bibliographic Note 7. Repeated Games 7.1 The Repeated Prisoners Dilemma 7.2 A General Model of Repeated Garnet 7.3 Stationary Equilibria of Repeated Games with Complete State Information and Discounting 7.4 Repeated Games with Standard Information: Examples 7.5 General Feasibility Theorems for Standard Repeated Games 7.6 Finitely Repeated Games and the Role of Initial Doubt 7.7 Imperfect Observability of Moves 7.8 Repeated Wines in Large Decentralized Groups 7.9 Repeated Games with Incomplete Information 7.10 Continuous Time 7.11 Evolutionary Simulation of Repeated Games Exercises 8. Bargaining and Cooperation in Two-Person Games 8.1 Noncooperative Foundations of Cooperative Game Theory 8.2 Two-Person Bargaining Problems and the Nash Bargaining Solution 8.3 Interpersonal Comparisons of Weighted Utility 8.4 Transferable Utility 8.5 Rational Threats 8.6 Other Bargaining Solutions 8.7 An Alternating-Offer Bargaining Game 8.8 An Alternating-Offer Game with Incomplete Information 8.9 A Discrete Alternating-Offer Game 8.10 Renegotiation Exercises 9. Coalitions in Cooperative Games 9.1 Introduction to Coalitional Analysis 9.2 Characteristic Functions with Transferable Utility 9.3 The Core 9.4 The Shapkey Value 9.5 Values with Cooperation Structures 9.6 Other Solution Concepts 9.7 Colational Games with Nontransferable Utility 9.8 Cores without Transferable Utility 9.9 Values without Transferable Utility Exercises Bibliographic Note 10. Cooperation under Uncertainty 10.1 Introduction 10.2 Concepts of Efficiency 10.3 An Example 10.4 Ex Post Inefficiency and Subsequent Oilers 10.5 Computing Incentive-Efficient Mechanisms 10.6 Inscrutability and Durability 10.7 Mechanism Selection by an Informed Principal 10.8 Neutral Bargaining Solutions 10.9 Dynamic Matching Processes with Incomplete Information Exercises Bibliography Index

博弈论 : 矛盾冲突分析 = Game theory : analysis of conflict

In the Hamadryas baboon, males are substantially larger than females. A troop of baboons is subdivided into a number of ‘one-male groups’, consisting of one adult male and one or more females with their young. The male prevents any of ‘his’ females from moving too far from him. Kummer (1971) performed the following experiment. Two males, A and B, previously unknown to each other, were placed in a large enclosure. Male A was free to move about the enclosure, but male B was shut in a small cage, from which he could observe A but not interfere. A female, unknown to both males, was then placed in the enclosure. Within 20 minutes male A had persuaded the female to accept his ownership. Male B was then released into the open enclosure. Instead of challenging male A , B avoided any contact, accepting A’s ownership.

Evolution and the Theory of Games

Learning and then recognizing a route, whether travelled during the day or at night, in clear or inclement weather, and in summer or winter is a challenging task for state of the art algorithms in computer vision and robotics. In this paper, we present a new approach to visual navigation under changing conditions dubbed SeqSLAM. Instead of calculating the single location most likely given a current image, our approach calculates the best candidate matching location within every local navigation sequence. Localization is then achieved by recognizing coherent sequences of these “local best matches”. This approach removes the need for global matching performance by the vision front-end - instead it must only pick the best match within any short sequence of images. The approach is applicable over environment changes that render traditional feature-based techniques ineffective. Using two car-mounted camera datasets we demonstrate the effectiveness of the algorithm and compare it to one of the most successful feature-based SLAM algorithms, FAB-MAP. The perceptual change in the datasets is extreme; repeated traverses through environments during the day and then in the middle of the night, at times separated by months or years and in opposite seasons, and in clear weather and extremely heavy rain. While the feature-based method fails, the sequence-based algorithm is able to match trajectory segments at 100% precision with recall rates of up to 60%.

SeqSLAM : visual route-based navigation for sunny summer days and stormy winter nights

Reinforcement learning (RL) algorithms have been around for decades and employed to solve various sequential decision-making problems. These algorithms, however, have faced great challenges when dealing with high-dimensional environments. The recent development of deep learning has enabled RL methods to drive optimal policies for sophisticated and capable agents, which can perform efficiently in these challenging environments. This article addresses an important aspect of deep RL related to situations that require multiple agents to communicate and cooperate to solve complex tasks. A survey of different approaches to problems related to multiagent deep RL (MADRL) is presented, including nonstationarity, partial observability, continuous state and action spaces, multiagent training schemes, and multiagent transfer learning. The merits and demerits of the reviewed methods will be analyzed and discussed with their corresponding applications explored. It is envisaged that this review provides insights about various MADRL methods and can lead to the future development of more robust and highly useful multiagent learning methods for solving real-world problems.

Deep Reinforcement Learning for Multiagent Systems: A Review of Challenges, Solutions, and Applications

In the past two decades, unmanned aerial vehicles (UAVs) have demonstrated their efficacy in supporting both military and civilian applications, where tasks can be dull, dirty, dangerous, or simply too costly with conventional methods. Many of the applications contain tasks that can be executed in parallel, hence the natural progression is to deploy multiple UAVs working together as a force multiplier. However, to do so requires autonomous coordination among the UAVs, similar to swarming behaviors seen in animals and insects. This paper looks at flocking with small fixed-wing UAVs in the context of a model-free reinforcement learning problem. In particular, Peng’s $Q(\lambda )$ with a variable learning rate is employed by the followers to learn a control policy that facilitates flocking in a leader-follower topology. The problem is structured as a Markov decision process, where the agents are modeled as small fixed-wing UAVs that experience stochasticity due to disturbances such as winds and control noises, as well as weight and balance issues. Learned policies are compared to ones solved using stochastic optimal control (i.e., dynamic programming) by evaluating the average cost incurred during flight according to a cost function. Simulation results demonstrate the feasibility of the proposed learning approach at enabling agents to learn how to flock in a leader-follower topology, while operating in a nonstationary stochastic environment.

A Q-Learning Approach to Flocking With UAVs in a Stochastic Environment

Crack detection and measurement in civil structures has been a constant field of research. Conventionally, a technician is responsible to detect and measure cracks in the field. In this paper, a system based on machine vision concepts has been developed with the goal to automate the crack measurement process. Using this method with only a single camera installed in a truck or even in a robot, a sequence of images is processed and the crack dimensions are estimated. The experimental results validate the application of the proposed method for real structures.

Automatic Crack Detection and Measurement Based on Image Analysis

In order for teams of unmanned aerial vehicles (UAVs) to collaborate and cooperate to perform challenging group tasks, intelligent and flexible control strategies are required. One of the complex behaviors required of a team of UAVs is dynamic encirclement, which is a tactic that can be employed for persistent surveillance and/or to neutralize a target by restricting its movement. This tactic requires a high level of cooperation such that the UAVs maintain a desired and proper encirclement radius and angular velocity around the target. In this paper, model predictive control (MPC) is used to model and implement controllers for the problem of dynamic encirclement. The linear and nonlinear control policies proposed in this paper are applied as a high-level controller to control multiple UAVs to encircle a desired target in simulations and real-time experiments with quadrotors. The nonlinear solution provides a theoretical analysis of the problem, while the linear control policy is used for real-time operation via a combination of MPC and feedback linearization applied to the nonlinear UAV system. The contributions of this paper lie in the implementation of MPC to solve the problem of dynamic encirclement of a team of UAVs in real time and the application of theoretical stability analysis to the problem.

Solving Multi-UAV Dynamic Encirclement via Model Predictive Control

Stereo vision is widely used in many 3-D image applications In this paper, we present a methodology to estimate the localization of objects in 3-D scenes using collaborative robots Using this method, the robots are able to measure the location of objects using only a single camera installed on each one of them From one pair of images, each one acquired by a different robot, the method locates homologous points, and then rebuilds the object by using equations for coordinate transformations The experimental results validate the application of the proposed method for the measurement of the pose of objects in autonomous robotic applications

Vision-Based Measurement for Localization of Objects in 3-D for Robotic Applications

Encirclement is a tactic that can be employed by a team of UAVs to neutralize a target by restricting its movement. The aim of the UAV team encircling the target is to move close to the target and maintain a formation around the target. In this paper, the problem of creating a dynamic circular formation around a target is considered, and a Decentralized Model Predictive Control (DMPC) policy is formulated. It is shown through simulation results that the derived MPC policy is effective for the case of a single UAV encircling a stationary target, a single UAV encircling a moving target, and a group of UAVs encircling a stationary target. The contributions of this paper are the application of MPC to the problem of encirclement, and the explicit objective of a dynamic circular formation around the target.

Sidney N. Givigi

Papers

A Q-Learning Approach to Flocking With UAVs in a Stochastic Environment

Automatic Crack Detection and Measurement Based on Image Analysis

Solving Multi-UAV Dynamic Encirclement via Model Predictive Control

Vision-Based Measurement for Localization of Objects in 3-D for Robotic Applications

Model Predictive Control for the dynamic encirclement of a target