Starcraft II is a popular real-time strategy (RTS) game, in which players compete with each other online. Based on their performance, the players are ranked in one of seven leagues. In our research, we aim at constructing a player model that is capable of predicting the league in which a player competes, using observations of their in-game behavior. Based on cognitive research and our knowledge of the game, we extracted from 1297 game replays a number of features that describe skill. After a preliminary test, we selected the SMO classifier to construct a player model, which achieved a weighted accuracy of 47.3% (SD 2.2). This constitutes a significant improvement over the weighted baseline of 25.5% (SD 1.1). We tested from what moment in the game it is possible to predict a player's skill, which we found is after about 2.5 minutes of gameplay, i.e., even before the players have confronted each other within the game. We conclude that our model can predict a player's skill early in the game.
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.
After a muted three-game Opening Day over the weekend, Major League Baseball's season gets into full swing Monday with 24 teams scheduled to play 12 games throughout the day. While nobody knows which team will come out on top this season, one thing is certain: MLB players will be compensated handsomely. Baseball's average salary on Opening Day 2016 is 4.38 million, an uptick of 4.4 percent over last year, according to a study of contract terms by the Associated Press. Baseball contracts can famously feature eye-popping figures, a theme commonly associated with Yankees designated hitter Alex Rodriguez, who has signed a couple of massive deals and will have made about 420 million in on-field earnings by his planned retirement in 2017. The massive contracts keep coming, and that helped fuel the rise in MLB's average salary.
Those behind the Overwatch players association haven't shared as much information about their efforts, but they plan to release formal details in around four months. The push is being led by Overwatch coach and former player Thomas "Morte" Kerbusch and sports labor attorney Ellen Zavian. Sports Business Journal says that the Overwatch association will likely be modeled after other US unions like the NFL Players Association. "I don't see this [players association] as any different than any other PA just because it's eSports," Zavian said. "So this isn't something that will be a lighthearted step.