We can evaluate features of problems and their potential solutions well before we can effectively solve them. When considering a game we have never played, for instance, we might infer whether it is likely to be challenging, fair, or fun simply from hearing the game rules, prior to deciding whether to invest time in learning the game or trying to play it well. Many studies of game play have focused on optimality and expertise, characterizing how people and computational models play based on moderate to extensive search and after playing a game dozens (if not thousands or millions) of times. Here, we study how people reason about a range of simple but novel connect-n style board games. We ask people to judge how fair and how fun the games are from very little experience: just thinking about the game for a minute or so, before they have ever actually played with anyone else, and we propose a resource-limited model that captures their judgments using only a small number of partial game simulations and almost no lookahead search.

PokerKit is an open-source Python library designed to overcome the restrictions of existing poker game simulation and hand evaluation tools, which typically support only a handful of poker variants and lack flexibility in game state control. In contrast, PokerKit significantly expands this scope by supporting an extensive array of poker variants and it provides a flexible architecture for users to define their custom games. This paper details the design and implementation of PokerKit, including its intuitive programmatic API, multi-variant game support, and a unified hand evaluation suite across different hand types. The flexibility of PokerKit allows for applications in diverse areas, such as poker AI development, tool creation, and online poker casino implementation. PokerKit's reliability has been established through static type checking, extensive doctests, and unit tests, achieving 99% code coverage. The introduction of PokerKit represents a significant contribution to the field of computer poker, fostering future research and advanced AI development for a wide variety of poker games. The source code is available at https://github.com/uoftcprg/pokerkit

We refer to the paper Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model and to this official DeepMind pseudocode for the coding part. The MuZero algorithm combines a tree-based search with a learned model, achieving superhuman performance in a variety of visually complex domains, without any knowledge of their underlying dynamics. We will give a brief explanation of how MuZero works, using diagrams as intuitive support. MuZero is an algorithm for mastering games like Go, Chess, Shogi and Atari without explicitly knowing the rules, thanks to its ability to plan winning strategies in unspecified environments. Trying to overcome the limitations of previous algorithms like AlphaZero, MuZero does not model the entire environment, it just models aspects that are crucial to the agent's decision-making process: the value (how good is the current position), the policy (which action is the best to take) and the reward (how good was last action).

Furyion Games used Unity Game Simulation to playtest its forthcoming shooter, 'Death Carnival' Unity's newest tool allows game developers to run cloud-based playtests at unprecedented speed and scale with machine learning. T0day, as part of the Google for Games Developer Summit, Unity Technologies announced Unity Game Simulation. It's a tool that stands to revolutionize playtesting--the process of playing a game to test it for bugs and flaws before it launches--for studios, with implications that extend far beyond the world of entertainment. In essence, Game Simulation equips game developers with the ability to create simulations with bots that playtest games on their behalf. Bots have been playing games effectively for decades, but Game Simulation harnesses them at a scale that is many orders of magnitude beyond what has been possible before.

Dataflow is a great tool for building out scalable data pipelines, but it can also be useful in different domains, such as scientific computing. One of the ways that I've been using Google's Cloud Dataflow tool recently is for simulating gameplay of different automated players. Years ago I built an automated Tetris player as part of the AI course at Cal Poly. I used a metaheuristic search approach, which required significant training time to learn the best values for the hyperparameters. I was able to code a distributed version of the system to scale up the approach, but it took significant effort to deploy on the 20 machines in the lab.

Over the last few years, the quest to build fully autonomous vehicles has shifted into high gear. Yet, despite huge advances in both the sensors and artificial intelligence (AI) required to operate these cars, one thing has so far proved elusive: developing algorithms that can accurately and consistently identify objects, movements, and road conditions. As Mathew Monfort, a postdoctoral associate and researcher at the Massachusetts Institute of Technology (MIT) puts it: "An autonomous vehicle must actually function in the real world. However, it's extremely difficult and expensive to drive actual cars around to collect all the data necessary to make the technology completely reliable and safe." All of this is leading researchers down a different path: the use of game simulations and machine learning to build better algorithms and smarter vehicles.