Artificial intelligence (AI) has become a part of everyday conversation and our lives. It is considered as the new electricity that is revolutionizing the world. AI is heavily invested in both industry and academy. However, there is also a lot of hype in the current AI debate. AI based on so-called deep learning has achieved impressive results in many problems, but its limits are already visible. AI has been under research since the 1940s, and the industry has seen many ups and downs due to over-expectations and related disappointments that have followed. The purpose of this book is to give a realistic picture of AI, its history, its potential and limitations. We believe that AI is a helper, not a ruler of humans. We begin by describing what AI is and how it has evolved over the decades. After fundamentals, we explain the importance of massive data for the current mainstream of artificial intelligence. The most common representations for AI, methods, and machine learning are covered. In addition, the main application areas are introduced. Computer vision has been central to the development of AI. The book provides a general introduction to computer vision, and includes an exposure to the results and applications of our own research. Emotions are central to human intelligence, but little use has been made in AI. We present the basics of emotional intelligence and our own research on the topic. We discuss super-intelligence that transcends human understanding, explaining why such achievement seems impossible on the basis of present knowledge,and how AI could be improved. Finally, a summary is made of the current state of AI and what to do in the future. In the appendix, we look at the development of AI education, especially from the perspective of contents at our own university.
We consider the task of building strong but human-like policies in multi-agent decision-making problems, given examples of human behavior. Imitation learning is effective at predicting human actions but may not match the strength of expert humans, while self-play learning and search techniques (e.g. AlphaZero) lead to strong performance but may produce policies that are difficult for humans to understand and coordinate with. We show in chess and Go that regularizing search policies based on the KL divergence from an imitation-learned policy by applying Monte Carlo tree search produces policies that have higher human prediction accuracy and are stronger than the imitation policy. We then introduce a novel regret minimization algorithm that is regularized based on the KL divergence from an imitation-learned policy, and show that applying this algorithm to no-press Diplomacy yields a policy that maintains the same human prediction accuracy as imitation learning while being substantially stronger.
Lookahead search has been a critical component of recent AI successes, such as in the games of chess, go, and poker. However, the search methods used in these games, and in many other settings, are tabular. Tabular search methods do not scale well with the size of the search space, and this problem is exacerbated by stochasticity and partial observability. In this work we replace tabular search with online model-based fine-tuning of a policy neural network via reinforcement learning, and show that this approach outperforms state-of-the-art search algorithms in benchmark settings. In particular, we use our search algorithm to achieve a new state-of-the-art result in self-play Hanabi, and show the generality of our algorithm by also showing that it outperforms tabular search in the Atari game Ms. Pacman.
The construction of approximate replication strategies for derivative contracts in incomplete markets is a key problem of financial engineering. Recently Reinforcement Learning algorithms for pricing and hedging under realistic market conditions have attracted significant interest. While financial research mostly focused on variations of Q-learning, in Artificial Intelligence Monte Carlo Tree Search is the recognized stateof-the-art method for various planning problems, such as the games of Hex, Chess, Go,... This article introduces Monte Carlo Tree Search as a method to solve the stochastic optimal control problem underlying the pricing and hedging of financial derivatives. As compared to Q-learning it combines reinforcement learning with tree search techniques. As a consequence Monte Carlo Tree Search has higher sample efficiency, is less prone to over-fitting to specific market models and generally learns stronger policies faster. In our experiments we find that Monte Carlo Tree Search, being the world-champion in games like Chess and Go, is easily capable of directly maximizing the utility of investor's terminal wealth without an intermediate mathematical theory.
The AlphaGo, AlphaGo Zero, and AlphaZero series of algorithms are a remarkable demonstration of deep reinforcement learning's capabilities, achieving superhuman performance in the complex game of Go with progressively increasing autonomy. However, many obstacles remain in the understanding of and usability of these promising approaches by the research community. Toward elucidating unresolved mysteries and facilitating future research, we propose ELF OpenGo, an open-source reimplementation of the AlphaZero algorithm. ELF OpenGo is the first open-source Go AI to convincingly demonstrate superhuman performance with a perfect (20:0) record against global top professionals. We apply ELF OpenGo to conduct extensive ablation studies, and to identify and analyze numerous interesting phenomena in both the model training and in the gameplay inference procedures. Our code, models, selfplay datasets, and auxiliary data are publicly available.
Using these libraries will help us focus only on the most interesting task: creating the algorithm that finds the best move. We'll start by creating a function that just returns a random move from all of the possible moves: Although this algorithm isn't a very solid chess player, it's a good starting point, as we can actually play against it: Now let's try to understand which side is stronger in a certain position. With the evaluation function, we're able to create an algorithm that chooses the move that gives the highest evaluation: The only tangible improvement is that our algorithm will now capture a piece if it can. Next we're going to create a search tree from which the algorithm can chose the best move. This is done by using the Minimax algorithm.
This book presents a methodology and philosophy of empirical science based on large scale lossless data compression. In this view a theory is scientific if it can be used to build a data compression program, and it is valuable if it can compress a standard benchmark database to a small size, taking into account the length of the compressor itself. This methodology therefore includes an Occam principle as well as a solution to the problem of demarcation. Because of the fundamental difficulty of lossless compression, this type of research must be empirical in nature: compression can only be achieved by discovering and characterizing empirical regularities in the data. Because of this, the philosophy provides a way to reformulate fields such as computer vision and computational linguistics as empirical sciences: the former by attempting to compress databases of natural images, the latter by attempting to compress large text databases. The book argues that the rigor and objectivity of the compression principle should set the stage for systematic progress in these fields. The argument is especially strong in the context of computer vision, which is plagued by chronic problems of evaluation. The book also considers the field of machine learning. Here the traditional approach requires that the models proposed to solve learning problems be extremely simple, in order to avoid overfitting. However, the world may contain intrinsically complex phenomena, which would require complex models to understand. The compression philosophy can justify complex models because of the large quantity of data being modeled (if the target database is 100 Gb, it is easy to justify a 10 Mb model). The complex models and abstractions learned on the basis of the raw data (images, language, etc) can then be reused to solve any specific learning problem, such as face recognition or machine translation.
E.A. Feigenbaum and J. Feldman (Eds.). Computers and Thought. McGraw-Hill, 1963. This collection includes twenty classic papers by such pioneers as A. M. Turing and Marvin Minsky who were behind the pivotal advances in artificially simulating human thought processes with computers. All Parts are available as downloadable pdf files; most individual chapters are also available separately. COMPUTING MACHINERY AND INTELLIGENCE. A. M. Turing. CHESS-PLAYING PROGRAMS AND THE PROBLEM OF COMPLEXITY. Allen Newell, J.C. Shaw and H.A. Simon. SOME STUDIES IN MACHINE LEARNING USING THE GAME OF CHECKERS. A. L. Samuel. EMPIRICAL EXPLORATIONS WITH THE LOGIC THEORY MACHINE: A CASE STUDY IN HEURISTICS. Allen Newell J.C. Shaw and H.A. Simon. REALIZATION OF A GEOMETRY-THEOREM PROVING MACHINE. H. Gelernter. EMPIRICAL EXPLORATIONS OF THE GEOMETRY-THEOREM PROVING MACHINE. H. Gelernter, J.R. Hansen, and D. W. Loveland. SUMMARY OF A HEURISTIC LINE BALANCING PROCEDURE. Fred M. Tonge. A HEURISTIC PROGRAM THAT SOLVES SYMBOLIC INTEGRATION PROBLEMS IN FRESHMAN CALCULUS. James R. Slagle. BASEBALL: AN AUTOMATIC QUESTION ANSWERER. Green, Bert F. Jr., Alice K. Wolf, Carol Chomsky, and Kenneth Laughery. INFERENTIAL MEMORY AS THE BASIS OF MACHINES WHICH UNDERSTAND NATURAL LANGUAGE. Robert K. Lindsay. PATTERN RECOGNITION BY MACHINE. Oliver G. Selfridge and Ulric Neisser. A PATTERN-RECOGNITION PROGRAM THAT GENERATES, EVALUATES, AND ADJUSTS ITS OWN OPERATORS. Leonard Uhr and Charles Vossler. GPS, A PROGRAM THAT SIMULATES HUMAN THOUGHT. Allen Newell and H.A. Simon. THE SIMULATION OF VERBAL LEARNING BEHAVIOR. Edward A. Feigenbaum. PROGRAMMING A MODEL OF HUMAN CONCEPT FORMULATION. Earl B. Hunt and Carl I. Hovland. SIMULATION OF BEHAVIOR IN THE BINARY CHOICE EXPERIMENT Julian Feldman. A MODEL OF THE TRUST INVESTMENT PROCESS. Geoffrey P. E. Clarkson. A COMPUTER MODEL OF ELEMENTARY SOCIAL BEHAVIOR. John T. Gullahorn and Jeanne E. Gullahorn. TOWARD INTELLIGENT MACHINES. Paul Armer. STEPS TOWARD ARTIFICIAL INTELLIGENCE. Marvin Minsky. A SELECTED DESCRIPTOR-INDEXED BIBLIOGRAPHY TO THE LITERATURE ON ARTIFICIAL INTELLIGENCE. Marvin Minsky.