Video games have served as useful benchmarks for the decision making community, but going beyond Atari games towards training agents in modern games has been prohibitively expensive for the vast majority of the research community. Recent progress in the research, development and open release of large vision models has the potential to amortize some of these costs across the community. However, it is currently unclear which of these models have learnt representations that retain information critical for sequential decision making. Towards enabling wider participation in the research of gameplaying agents in modern games, we present a systematic study of imitation learning with publicly available visual encoders compared to the typical, task-specific, end-to-end training approach in Minecraft, Minecraft Dungeons and Counter-Strike: Global Offensive.
In fair classification, it is common to train a model, and to compare and correct subgroup-specific error rates for disparities. However, even if a model's classification decisions satisfy a fairness metric, it is not necessarily the case that these decisions are equally confident. This becomes clear if we measure variance: We can fix everything in the learning process except the subset of training data, train multiple models, measure (dis)agreement in predictions for each test example, and interpret disagreement to mean that the learning process is more unstable with respect to its classification decision. Empirically, some decisions can in fact be so unstable that they are effectively arbitrary. To reduce this arbitrariness, we formalize a notion of self-consistency of a learning process, develop an ensembling algorithm that provably increases self-consistency, and empirically demonstrate its utility to often improve both fairness and accuracy. Further, our evaluation reveals a startling observation: Applying ensembling to common fair classification benchmarks can significantly reduce subgroup error rate disparities, without employing common pre-, in-, or post-processing fairness interventions. Taken together, our results indicate that variance, particularly on small datasets, can muddle the reliability of conclusions about fairness. One solution is to develop larger benchmark tasks. To this end, we release a toolkit that makes the Home Mortgage Disclosure Act datasets easily usable for future research.
The advent of machine learning models that surpass human decision-making ability in complex domains has initiated a movement towards building AI systems that interact with humans. Many building blocks are essential for this activity, with a central one being the algorithmic characterization of human behavior. While much of the existing work focuses on aggregate human behavior, an important long-range goal is to develop behavioral models that specialize to individual people and can differentiate among them. To formalize this process, we study the problem of behavioral stylometry, in which the task is to identify a decision-maker from their decisions alone. We present a transformer-based approach to behavioral stylometry in the context of chess, where one attempts to identify the player who played a set of games. Our method operates in a few-shot classification framework, and can correctly identify a player from among thousands of candidate players with 98% accuracy given only 100 labeled games. Even when trained on amateur play, our method generalises to out-of-distribution samples of Grandmaster players, despite the dramatic differences between amateur and world-class players. Finally, we consider more broadly what our resulting embeddings reveal about human style in chess, as well as the potential ethical implications of powerful methods for identifying individuals from behavioral data.
An emerging theme in artificial intelligence research is the creation of models to simulate the decisions and behavior of specific people, in domains including game-playing, text generation, and artistic expression. These models go beyond earlier approaches in the way they are tailored to individuals, and the way they are designed for interaction rather than simply the reproduction of fixed, pre-computed behaviors. We refer to these as mimetic models, and in this paper we develop a framework for characterizing the ethical and social issues raised by their growing availability. Our framework includes a number of distinct scenarios for the use of such models, and considers the impacts on a range of different participants, including the target being modeled, the operator who deploys the model, and the entities that interact with it.
We develop a new, principled algorithm for estimating the contribution of training data points to the behavior of a deep learning model, such as a specific prediction it makes. Our algorithm estimates the AME, a quantity that measures the expected (average) marginal effect of adding a data point to a subset of the training data, sampled from a given distribution. When subsets are sampled from the uniform distribution, the AME reduces to the well-known Shapley value. Our approach is inspired by causal inference and randomized experiments: we sample different subsets of the training data to train multiple submodels, and evaluate each submodel's behavior. We then use a LASSO regression to jointly estimate the AME of each data point, based on the subset compositions. Under sparsity assumptions ($k \ll N$ datapoints have large AME), our estimator requires only $O(k\log N)$ randomized submodel trainings, improving upon the best prior Shapley value estimators.
We observe that many system policies that make threshold decisions involving a resource (e.g., time, memory, cores) naturally reveal additional, or implicit feedback. For example, if a system waits X min for an event to occur, then it automatically learns what would have happened if it waited <X min, because time has a cumulative property. This feedback tells us about alternative decisions, and can be used to improve the system policy. However, leveraging implicit feedback is difficult because it tends to be one-sided or incomplete, and may depend on the outcome of the event. As a result, existing practices for using feedback, such as simply incorporating it into a data-driven model, suffer from bias. We develop a methodology, called Sayer, that leverages implicit feedback to evaluate and train new system policies. Sayer builds on two ideas from reinforcement learning -- randomized exploration and unbiased counterfactual estimators -- to leverage data collected by an existing policy to estimate the performance of new candidate policies, without actually deploying those policies. Sayer uses implicit exploration and implicit data augmentation to generate implicit feedback in an unbiased form, which is then used by an implicit counterfactual estimator to evaluate and train new policies. The key idea underlying these techniques is to assign implicit probabilities to decisions that are not actually taken but whose feedback can be inferred; these probabilities are carefully calculated to ensure statistical unbiasedness. We apply Sayer to two production scenarios in Azure, and show that it can evaluate arbitrary policies accurately, and train new policies that outperform the production policies.
Even when machine learning systems surpass human ability in a domain, there are many reasons why AI systems that capture human-like behavior would be desirable: humans may want to learn from them, they may need to collaborate with them, or they may expect them to serve as partners in an extended interaction. Motivated by this goal of human-like AI systems, the problem of predicting human actions -- as opposed to predicting optimal actions -- has become an increasingly useful task. We extend this line of work by developing highly accurate personalized models of human behavior in the context of chess. Chess is a rich domain for exploring these questions, since it combines a set of appealing features: AI systems have achieved superhuman performance but still interact closely with human chess players both as opponents and preparation tools, and there is an enormous amount of recorded data on individual players. Starting with an open-source version of AlphaZero trained on a population of human players, we demonstrate that we can significantly improve prediction of a particular player's moves by applying a series of fine-tuning adjustments. The differences in prediction accuracy between our personalized models and unpersonalized models are at least as large as the differences between unpersonalized models and a simple baseline. Furthermore, we can accurately perform stylometry -- predicting who made a given set of actions -- indicating that our personalized models capture human decision-making at an individual level.
As artificial intelligence becomes increasingly intelligent---in some cases, achieving superhuman performance---there is growing potential for humans to learn from and collaborate with algorithms. However, the ways in which AI systems approach problems are often different from the ways people do, and thus may be uninterpretable and hard to learn from. A crucial step in bridging this gap between human and artificial intelligence is modeling the granular actions that constitute human behavior, rather than simply matching aggregate human performance. We pursue this goal in a model system with a long history in artificial intelligence: chess. The aggregate performance of a chess player unfolds as they make decisions over the course of a game. The hundreds of millions of games played online by players at every skill level form a rich source of data in which these decisions, and their exact context, are recorded in minute detail. Applying existing chess engines to this data, including an open-source implementation of AlphaZero, we find that they do not predict human moves well. We develop and introduce Maia, a customized version of Alpha-Zero trained on human chess games, that predicts human moves at a much higher accuracy than existing engines, and can achieve maximum accuracy when predicting decisions made by players at a specific skill level in a tuneable way. For a dual task of predicting whether a human will make a large mistake on the next move, we develop a deep neural network that significantly outperforms competitive baselines. Taken together, our results suggest that there is substantial promise in designing artificial intelligence systems with human collaboration in mind by first accurately modeling granular human decision-making.