Important insights towards the explainability of neural networks reside in the characteristics of their decision boundaries. In this work, we borrow tools from the field of adversarial robustness, and propose a new perspective that relates dataset features to the distance of samples to the decision boundary. This enables us to carefully tweak the position of the training samples and measure the induced changes on the boundaries of CNNs trained on large-scale vision datasets. We use this framework to reveal some intriguing properties of CNNs. Specifically, we rigorously confirm that neural networks exhibit a high invariance to non-discriminative features, and show that the decision boundaries of a DNN can only exist as long as the classifier is trained with some features that hold them together. Finally, we show that the construction of the decision boundary is extremely sensitive to small perturbations of the training samples, and that changes in certain directions can lead to sudden invariances in the orthogonal ones. This is precisely the mechanism that adversarial training uses to achieve robustness.

Complex games have long been an important benchmark for testing the progress of artificial intelligence algorithms. AlphaGo, AlphaZero, and MuZero have defeated top human players in Go and Chess, garnering widespread societal attention towards artificial intelligence. Concurrently, large language models (LLMs) have exhibited remarkable capabilities across various tasks, raising the question of whether LLMs can achieve similar success in complex games. In this paper, we explore the potential of LLMs in mastering complex card games. We systematically assess the learning capabilities of LLMs across eight diverse card games, evaluating the impact of fine-tuning on high-quality gameplay data, and examining the models' ability to retain general capabilities while mastering these games. Our findings indicate that: (1) LLMs can approach the performance of strong game AIs through supervised fine-tuning on high-quality data, (2) LLMs can achieve a certain level of proficiency in multiple complex card games simultaneously, with performance augmentation for games with similar rules and conflicts for dissimilar ones, and (3) LLMs experience a decline in general capabilities when mastering complex games, but this decline can be mitigated by integrating a certain amount of general instruction data. The evaluation results demonstrate strong learning ability and versatility of LLMs. The code is available at https://github.com/THUDM/LLM4CardGame

Flexibility is an essential part of staying fit. Breakthroughs, discoveries, and DIY tips sent every weekday. In your efforts to exercise, chances are you've worked on improving the four components of physical fitness. The problem is there are actually five . Criminally overlooked in the pursuit of big-ticket goals like strength, endurance, lung capacity and body composition is flexibility.

Chinese scientists have developed an artificial intelligence (AI) program that is quick-minded and on par with professional human players in heads-up no-limit Texas hold'em poker. Named AlphaHoldem, the AI program has achieved the level of sophisticated human players through a 10,000-hand two-player competition after three days of self-training, according to a paper which will be presented in February next year at AAAI 2022 global AI conference in Vancouver, Canada. Texas hold'em is a popular poker game in which players often deceive and bluff. It is more similar to real-world problems than Go or Weiqi and chess since decisions are made with imperfect information. The researchers from the Institute of Automation under the Chinese Academy of Sciences (CAS) reported that AlphaHoldem, a fast learner, used only about three to four milliseconds for each movement, about 1,000 times quicker than that of first-generation AI hold'em players DeepStack and Libratus.

Like many forms of entertainment within the software space, the world of iGaming is one that relies on the application of artificial intelligence technology. Setting this industry apart from its contemporaries is just how deep the AI-iGaming connection runs in the key facets of its regular operation. In this article, we want to explore two of the most important of these avenues, to uncover just how crucial the integration of these systems has become. Perhaps the most common use of AI with iGaming is seen with game testing. As a part of the software utilized to ensure platform reliability and statistical consistency, AI systems in these instances are implemented to perform work that would traditionally be performed by humans.

RLCard is an open-source toolkit for reinforcement learning research in card games. It supports various card environments with easy-to-use interfaces, including Blackjack, Leduc Hold'em, Texas Hold'em, UNO, Dou Dizhu and Mahjong. The goal of RLCard is to bridge reinforcement learning and imperfect information games, and push forward the research of reinforcement learning in domains with multiple agents, large state and action space, and sparse reward. In this paper, we provide an overview of the key components in RLCard, a discussion of the design principles, a brief introduction of the interfaces, and comprehensive evaluations of the environments.

Evaluating agent performance when outcomes are stochastic and agents use randomized strategies can be challenging when there is limited data available. The variance of sampled outcomes may make the simple approach of Monte Carlo sampling inadequate. This is the case for agents playing heads-up no-limit Texas hold'em poker, whereman-machine competitions typically involve multiple days of consistent play by multiple players, but still can (and sometimes did) result in statistically insignificant conclusions. In this paper, we introduce AIVAT, a low variance, provably unbiased value assessment tool that exploits an arbitrary heuristic estimate of state value, as well as the explicit strategy of a subset of the agents. Unlike existing techniques which reduce the variance from chance events, or only consider game ending actions, AIVAT reduces the variance both from choices by nature and by players with a known strategy. The resulting estimator produces results that significantly outperform previous state of the art techniques. It was able to reduce the standard deviation of a Texas hold'em poker man-machine match by 85\% and consequently requires 44 times fewer games to draw the same statistical conclusion. AIVAT enabled the first statistically significant AI victory against professional poker players in no-limit hold'em.Furthermore, the technique was powerful enough to produce statistically significant results versus individual players, not just an aggregate pool of the players. We also used AIVAT to analyze a short series of AI vs human poker tournaments,producing statistical significant results with as few as 28 matches.

A bunch of top poker pros are getting ready to take on Libratus, the latest and greatest poker bot, in a 20-day Heads-Up No-Limit Texas Hold'em challenge. Since the bot's predecessor, Claudico, was almost good enough to beat top players, and Libratus is supposed to be a lot better, the humans could be in trouble. On the other hand, humans are getting better, too, says competitor Jason Les. "From the human side, poker has gotten much tougher in the last 20 months," Les told Carnegie Mellon University, which developed the bot. Les says that humans are getting better at poker thanks to computer-assisted analysis tools like PioSOLVER and PokerSnowie.

In many imperfect information games, the ability to exploit the opponent is crucial for achieving high performance. For instance, skilled poker players usually capitalize on various weaknesses in their opponents’ playing patterns and styles to maximize their earnings. Therefore, it is important to enable computer players in such games to identify flaws in opponent strategies and adapt their behaviors to exploit these flaws. This paper presents a genetic algorithm to evolve adaptive LSTM (Long Short Term Memory) poker players featuring effective opponent exploitation. Experimental results in heads-up no-limit Texas Hold’em demonstrate that adaptive LSTM players are able to obtain 40% to 1360% more earnings than cutting-edge game theoretic poker players against opponents with various flawed strategies. In addition, experimental results indicate that adaptive LSTM players evolved through playing against simple and weak rule-based opponents can achieve comparable performance against top game-theoretic poker players. The approach introduced in this paper is a promising start for building adaptive computer players for imperfect information games.

Evaluating agent performance when outcomes are stochastic and agents use randomized strategies can be challenging when there is limited data available. The variance of sampled outcomes may make the simple approach of Monte Carlo sampling inadequate. This is the case for agents playing heads-up no-limit Texas hold'em poker, where man-machine competitions have involved multiple days of consistent play and still not resulted in statistically significant conclusions even when the winner's margin is substantial. In this paper, we introduce AIVAT, a low variance, provably unbiased value assessment tool that uses an arbitrary heuristic estimate of state value, as well as the explicit strategy of a subset of the agents. Unlike existing techniques which reduce the variance from chance events, or only consider game ending actions, AIVAT reduces the variance both from choices by nature and by players with a known strategy. The resulting estimator in no-limit poker can reduce the number of hands needed to draw statistical conclusions by more than a factor of 10.