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.

We evaluate the use of original game curricula supported by the Atari 2600 console as a heterogeneous transfer benchmark for deep reinforcement learning agents. Game designers created curricula using combinations of several discrete modifications to the basic versions of games such as Space Invaders, Breakout and Freeway, making them progressively more challenging for human players. By formally organising these modifications into several factors of variation, we are able to show that Analyses of Variance (ANOVA) are a potent tool for studying the effects of human-relevant domain changes on the learning and transfer performance of a deep reinforcement learning agent. Since no manual task engineering is needed on our part, leveraging the original multi-factorial design avoids the pitfalls of unintentionally biasing the experimental setup. We find that game design factors have a large and statistically significant impact on an agent's ability to learn, and so do their combinatorial interactions. Furthermore, we show that zero-shot transfer from the basic games to their respective variations is possible, but the variance in performance is also largely explained by interactions between factors. As such, we argue that Atari game curricula offer a challenging benchmark for transfer learning in RL, that can help the community better understand the generalisation capabilities of RL agents along dimensions which meaningfully impact human generalisation performance. As a start, we report that value-function finetuning of regularly trained agents achieves positive transfer in a majority of cases, but significant headroom for algorithmic innovation remains. We conclude with the observation that selective transfer from multiple variants could further improve performance.

Game designers can use computer-aided game design methods to quantitatively compare player skill levels, different game variants, and learning rates, for the purpose of modeling how players will likely experience a game. We use Monte-Carlo simulation, hazard functions, and survival analysis to show how difficulty will quantitatively change throughout a game level as we vary skill, game parameters, and learning rates. We give a mathematical overview of survival analysis, present empirical data analyses of our player models for each game variant, and provide theoretical probability distributions for each game. This analysis shows the quantitative reasons why balancing a game for a wide range of player skill can be difficult; our player modeling provides tools for tuning this game balance. We also analyze the score distribution of over 175 million play sessions of a popular online Flappy Bird variant to demonstrate how learning effects can impact scores, implying that learning is crucial aspect of player modeling.

In previous work, artificial agents were shown to achieve almost perfect accuracy in referential games where they have to communicate to identify images. Nevertheless, the resulting communication protocols rarely display salient features of natural languages, such as compositionality. In this paper, we propose some realistic sources of pressure on communication that avert this outcome. More specifically, we formalise the principle of least effort through an auxiliary objective. Moreover, we explore several game variants, inspired by the principle of object constancy, in which we alter the frequency, position, and luminosity of the objects in the images. We perform an extensive analysis on their effect through compositionality metrics, diagnostic classifiers, and zero-shot evaluation. Our findings reveal that the proposed sources of pressure result in emerging languages with less redundancy, more focus on high-level conceptual information, and better abilities of generalisation. Overall, our contributions reduce the gap between emergent and natural languages.

Game designers can use computer-aided game design methods to quantitatively compare player skill levels, different game variants, and learning rates, for the purpose of modeling how players will likely experience a game. We use Monte-Carlo simulation, hazard functions, and survival analysis to show how difficulty will quantitatively change throughout a game level as we vary skill, game parameters, and learning rates. We give a mathematical overview of survival analysis, present empirical data analyses of our player models for each game variant, and provide theoretical probability distributions for each game. This analysis shows the quantitative reasons why balancing a game for a wide range of player skill can be difficult; our player modeling provides tools for tuning this game balance. We also analyze the score distribution of over 175 million play sessions of a popular online Flappy Bird variant to demonstrate how learning effects can impact scores, implying that learning is crucial aspect of player modeling.