In this post, we continue our summaries of the invited talks from the International Joint Conference on Artificial Intelligence (IJCAI-21). This time, we cover the presentations from Yoshua Bengio and Michael Thielscher. Yoshua's talk focussed on the development of what he calls system 2 deep learning. The aim is to incorporate agency, causality, and ideas from human intelligence to advance current deep learning methods, thus enabling better out-of-distribution generalisation. As proposed by Daniel Kahneman, system 1 and system 2 are different types of thinking.

General Game Playing is a field which allows the researcher to investigate techniques that might eventually be used in an agent capable of Artificial General Intelligence.  Game playing presents a controlled environment in which to evaluate AI techniques, and so we have seen an increase in interest in this field of research.  Games of imperfect information offer the researcher an additional challenge in terms of complexity over games with perfect information.  In this article, we look at imperfect-information games: their expression, their complexity, and the additional demands of their players.  We consider the problems of working with imperfect information and introduce a technique called HyperPlay, for efficiently sampling very large information sets, and present a formalism together with pseudo code so that others may implement it. We examine the design choices for the technique, show its soundness and completeness then provide some experimental results and demonstrate the use of the technique in a variety of imperfect-information games, revealing its strengths, weaknesses, and its efficiency against randomly generating samples.  Improving the technique, we present HyperPlay-II, capable of correctly valuing information-gathering moves.  Again, we provide some experimental results and demonstrate the use of the new technique revealing its strengths, weaknesses and its limitations.

While current General Game Playing (GGP) systems facilitate useful research in Artificial Intelligence (AI) for game-playing, they are often somewhat specialized and computationally inefficient. In this paper, we describe an initial version of a "ludemic" general game system called Ludii, which has the potential to provide an efficient tool for AI researchers as well game designers, historians, educators and practitioners in related fields. Ludii defines games as structures of ludemes, i.e. high-level, easily understandable game concepts. We establish the foundations of Ludii by outlining its main benefits: generality, extensibility, understandability and efficiency. Experimentally, Ludii outperforms one of the most efficient Game Description Language (GDL) reasoners, based on a propositional network, for all available games in the Tiltyard GGP repository.

The establishment of the International General Game Playing Competition in 2005, however, resulted in a renewed interest in more general problem-solving approaches to game playing. In general game playing (GGP) the goal is to create gameplaying systems that autonomously learn how to play a wide variety of games skillfully, given only the descriptions of the game rules. In this paper we review the history of the competition, discuss progress made so far, and list outstanding research challenges. Unlike specialized game players, such as Deep Blue (Campbell, Hoane, and Hsu 2002), general game players cannot rely on algorithms designed in advance for specific games; they must discover such algorithms themselves. General game playing expertise depends on intelligence on the part of the game player rather than intelligence of the programmer of the game player.

Google supercomputer AlphaGo outsmarted South Korean Go champion Lee Sedol, winning 4-1 in the best of five game series that came to an end on Tuesday, as people begin to wonder whether the ever-changing world of artificial intelligence (AI) will one day pose a threat to the human society. Michael Thielscher, a professor at Australia's University of New South Wales (UNSW), said the supercomputer can only play Go and is unable to do anything besides what it has been programmed for. "It's now better it seems than any human player but it's still only good at Go, and this is probably the biggest weakness of many existing artificial intelligence systems, that they lack what we call artificial general intelligence," Thielscher, a professor of computer science and engineering, told Xinhua. Google itself is a big believer in AI. In recent years, its self-driving cars have been gaining a lot of attention.

High-level programming languages are an influential control paradigm for building agents that are purposeful in an incompletely known world. GOLOG, for example, allows us to write programs, with loops, whose constructs refer to an explicit world model axiomatized in the expressive language of the situation calculus. Over the years, GOLOG has been extended to deal with many other features, the claim being that these would be useful in robotic applications. Unfortunately, when robots are actually deployed, effectors and sensors are noisy, typically characterized over continuous probability distributions, none of which is supported in GOLOG, its dialects or its cousins. This paper presents ALLEGRO, a belief-based programming language for stochastic domains, that refashions GOLOG to allow for discrete and continuous initial uncertainty and noise. It is fully implemented and experiments demonstrate that ALLEGRO could be the basis for bridging high-level programming and probabilistic robotics technologies in a general way.

General Game Playing aims to create AI systems that can understand the rules of new games and learn to play them effectively without human intervention. The recent proposal for general game-playing robots extends this to AI systems that play games in the real world. Execution monitoring becomes a necessity when moving from a virtual to a physical environment, because in reality actions may not be executed properly and (human) opponents may make illegal game moves. We develop a formal framework for execution monitoring by which an action theory that provides an axiomatic description of a game is automatically embedded in a meta-game for a robotic player — called the arbiter — whose role is to monitor and correct failed actions. This allows for the seamless encoding of recovery behaviours within a meta-game, enabling a robot to recover from these unexpected events.

A general game player is a system that can play previously unknown games just by being given their rules. For this purpose, the Game Description Language (GDL) has been developed as a high-level knowledge representation formalism to communicate game rules to players. In this paper, we address a fundamental limitation of state-of-the-art methods and systems for General Game Playing, namely, their being confined to deterministic games with complete information about the game state. We develop a simple yet expressive extension of standard GDL that allows for formalising the rules of arbitrary finite, n-player games with randomness and incomplete state knowledge. In the second part of the paper, we address the intricate reasoning challenge for general game-playing systems that comes with the new description language. We develop a full embedding of extended GDL into the Situation Calculus augmented by Scherl and Levesque's knowledge fluent. We formally prove that this provides a sound and complete reasoning method for players' knowledge about game states as well as about the knowledge of the other players.

We present a uniform non-monotonic solution to the problems of reasoning about action on the basis of an argumentation-theoretic approach. Our theory is provably correct relative to a sensible minimisation policy introduced on top of a temporal propositional logic. Sophisticated problem domains can be formalised in our framework. As much attention of researchers in the field has been paid to the traditional and basic problems in reasoning about actions such as the frame, the qualification and the ramification problems, approaches to these problems within our formalisation lie at heart of the expositions presented in this paper.

The Game Description Language is a high-level, rule-based formalisms for communicating the rules of arbitrary  games to general game-playing systems, whose challenging task is to learn to play previously unknown games without human intervention. Originally designed for deterministic games with complete information about the game state, the language was recently extended to include randomness and imperfect information. However, determining the extent to which this enhancement allows to describe truly arbitrary games was left as an open problem. We provide a positive answer to this question by relating the extended Game Description Language to the universal, mathematical concept of extensive-form games, proving that indeed just any such game can be described faithfully.