Collectible card games are challenging, widely played games that have received increasing attention from the AI research community in recent years. Despite important breakthroughs, the field still poses many unresolved challenges. This work aims to help further research on the genre by proposing a taxonomy of collectible card games by analyzing their rules, mechanics, and game modes from the perspective of game-playing AI research. To achieve this, we studied a set of popular games and provided a thorough discussion about their characteristics.

The goal of the game is to decrease While Poker, as a family of games, has been studied extensively in the opponent's health to zero. There are many popular collectible the last decades, collectible card games have seen relatively little card games, such as Magic: The Gathering [24], Hearthstone [3], attention. Only recently have we seen an agent that can compete The Elder Scrolls: Legends [20] and many others. A trait that makes with professional human players in Hearthstone, one of the most collectible card games appealing to human players and challenging popular collectible card games. Although artificial agents must be for AI agents is the broad range of ways to mix and match available able to work with imperfect information in both of these genres, cards into decks. Even small collectible card games with tens of collectible card games pose another set of distinct challenges. Unlike available cards can offer more potential decks than the total number in many poker variants, agents must deal with state space so vast of atoms in the universe [17].

This paper presents a new AI challenge, the Tales of Tribute AI Competition (TOTAIC), based on a two-player deck-building card game released with the High Isle chapter of The Elder Scrolls Online. Currently, there is no other AI competition covering Collectible Card Games (CCG) genre, and there has never been one that targets a deck-building game. Thus, apart from usual CCG-related obstacles to overcome, like randomness, hidden information, and large branching factor, the successful approach additionally requires long-term planning and versatility. The game can be tackled with multiple approaches, including classic adversarial search, single-player planning, and Neural Networks-based algorithms. This paper introduces the competition framework, describes the rules of the game, and presents the results of a tournament between sample AI agents. The first edition of TOTAIC is hosted at the IEEE Conference on Games 2023.

This paper concludes five years of AI competitions based on Legends of Code and Magic (LOCM), a small Collectible Card Game (CCG), designed with the goal of supporting research and algorithm development. The game was used in a number of events, including Community Contests on the CodinGame platform, and Strategy Card Game AI Competition at the IEEE Congress on Evolutionary Computation and IEEE Conference on Games. LOCM has been used in a number of publications related to areas such as game tree search algorithms, neural networks, evaluation functions, and CCG deckbuilding. We present the rules of the game, the history of organized competitions, and a listing of the participant and their approaches, as well as some general advice on organizing AI competitions for the research community. Although the COG 2022 edition was announced to be the last one, the game remains available and can be played using an online leaderboard arena.

Strategy card game is a well-known genre that is demanding on the intelligent game-play and can be an ideal test-bench for AI. Previous work combines an end-to-end policy function and an optimistic smooth fictitious play, which shows promising performances on the strategy card game Legend of Code and Magic. In this work, we apply such algorithms to Hearthstone, a famous commercial game that is more complicated in game rules and mechanisms. We further propose several improved techniques and consequently achieve significant progress. For a machine-vs-human test we invite a Hearthstone streamer whose best rank was top 10 of the official league in China region that is estimated to be of millions of players. Our models defeat the human player in all Best-of-5 tournaments of full games (including both deck building and battle), showing a strong capability of decision making.

Blizzard Entertainment will be suspending key games like Overwatch 2 and World of Warcraft in China because it failed to reach an agreement with partner NetEase, it announced. Those titles along with Hearthstone, Starcraft, Heroes of the Storm, Diablo III and Warcraft III: Reforged will be unavailable in China starting on January 23, 2023. Diablo Immortal, which arrived earlier this year, won't be affected as it's covered by a separate agreement, according to NetEase. "The two parties have not reached a deal to renew the agreements that is consistent with Blizzard's operating principles and commitments to players and employees, and the agreements are set to expire in January 2023," Blizzard said in the press release. "We will suspend new sales in the coming days and Chinese players will be receiving details of how this will work soon. Upcoming releases for World of Warcraft: Dragonflight, Hearthstone: March of the Lich King, and season 2 of Overwatch 2 will proceed later this year."

Eight years ago, Blizzard Entertainment launched Hearthstone, a free-to-play smartphone game that took elements of physical card battlers such as Magic: the Gathering and the Pokémon trading card game, and married them to the developer's Warcraft franchise. The result was a spectacular global success that inspired an endless slew of similar deck-building games, all based around the same idea: you start with a small pack of digital cards, each with different powers, and you place them on the board against an opponent with a different deck. Designed by Ben Brode, one of the co-creators of Hearthstone, Marvel Snap is a fresh take on the genre, in which players build collections of superheroes, each with different power ratings, and battle with a human or AI opponent to control three locations in the middle of the game board. The beauty is in the stripped-down simplicity of the interface: there are only six turns in each game, and only four cards can be placed at each location. As rounds progress, participants are able to place more powerful heroes.

The situation in front of me looks dire. Four minions sit on the board, none of which are my own. They have a range of attack points, an onslaught that will surely deplete my remaining health points. A rope flies across the middle of the screen, igniting on the left and burning toward the right, signaling the impending end of my turn. I need to move fast.

Blizzard Entertainment made true to its promise to host an online version of BlizzCon after the company was forced to cancel its in-person convention due to the pandemic caused by COVID-19. BlizzCon 2020 was supposed to take place later this year, but with the events that caused a worldwide dilemma has urged organizers to think of ways to still push through the annual event while observing guidelines set by health agencies and the government to curb the spread of the virus. "We're talking about how we might be able to channel the BlizzCon spirit and connect with you in some way online, far less impacted by the state of health and safety protocols for mass in-person gatherings," said BlizzCon Executive Producer Saralyn Smith in a May 26, 2020 blog post. Blizzard Entertainment's eSports World Championship competitions for "Hearthstone," "Heroes of the Storm," "World of Warcraft" and "StarCraft 2" will be held over an entire week later this year. Windows 10 has come on board as an official BlizzCon 2015 sponsor, with the opening ceremony streaming on Xbox One for the first time.

From a perspective on contrastive learning as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged encoder. This enables building a large and consistent dictionary on-the-fly that facilitates contrastive unsupervised learning. MoCo provides competitive results under the common linear protocol on ImageNet classification. More importantly, the representations learned by MoCo transfer well to downstream tasks. MoCo can outperform its supervised pre-training counterpart in 7 detection/segmentation tasks on PASCAL VOC, COCO, and other datasets, sometimes surpassing it by large margins. This suggests that the gap between unsupervised and supervised representation learning has been largely closed in many vision tasks.