Learning in Repeated Games: Human Versus Machine
نویسندگان
چکیده
While Artificial Intelligence has successfully outperformed humans in complex combinatorial games (such as chess and checkers), humans have retained their supremacy in social interactions that require intuition and adaptation, such as cooperation and coordination games. Despite significant advances in learning algorithms, most algorithms adapt at times scales which are not relevant for interactions with humans, and therefore the advances in AI on this front have remained of a more theoretical nature. This has also hindered the experimental evaluation of how these algorithms perform against humans, as the length of experiments needed to evaluate them is beyond what humans are reasonably expected to endure (max 100 repetitions). This scenario is rapidly changing, as recent algorithms are able to converge to their functional regimes in shorter time-scales. Additionally, this shift opens up possibilities for experimental investigation: where do humans stand compared with these new algorithms? We evaluate humans experimentally against a representative element of these fast-converging algorithms. Our results indicate that the performance of at least one of these algorithms is comparable to, and even exceeds, the performance of people.
منابع مشابه
Learning in real-time in repeated games using experts
Despite much progress, state-of-the-art learning algorithms for repeated games still often require thousands of moves to learn effectively – even in simple games. Our goal is to find algorithms that learn to play effective strategies in tens of moves in many games when paired against various associates. Toward this end, we describe a new meta-algorithm designed to increase the learning speed an...
متن کاملLearning and teaching in repeated games: A machine learning approach to long-term best-response play
Repeated games and long-term best-response play. We consider the problem of learning during a play of a a repeated game. Existing approaches often focus on algorithms that asymptotically achieve an equilibrium of the one-shot game. We shift away from that paradigm to consider learning strategies that attempt to play long-term best-response to the opponent’s observed strategy. This goal may be m...
متن کاملAn Initial Implementation of the Turing Tournament to Learning in Repeated Two
We report on a design of a Turing tournament and its initial implementation to learning in repeated 2 person games. The principal objectives of the tournament, named after the original Turing Test, are (1) to find learning algorithms (emulators) that most closely simulate human behavior, (2) to find algorithms (detectors) that most accurately distinguish between humans and machines, and (3) eve...
متن کاملMulti-agent Learning Experiments on Repeated Matrix Games
This paper experimentally evaluates multiagent learning algorithms playing repeated matrix games to maximize their cumulative return. Previous works assessed that Qlearning surpassed Nash-based multi-agent learning algorithms. Based on all-againstall repeated matrix game tournaments, this paper updates the state of the art of multiagent learning experiments. In a first stage, it shows that M-Qu...
متن کاملLearning in Repeated Games with Minimal Information: The Effects of Learning Bias
Automated agents for electricity markets, social networks, and other distributed networks must repeatedly interact with other intelligent agents, often without observing associates’ actions or payoffs (i.e., minimal information). Given this reality, our goal is to create algorithms that learn effectively in repeated games played with minimal information. As in other applications of machine lear...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1404.4985 شماره
صفحات -
تاریخ انتشار 2014