Artificial Intelligence (cs.AI)

Abstract: Analysis of invasive sports such as soccer is challenging because the game situation changes continuously in time and space, and multiple agents individually recognize the game situation and make decisions. Previous studies using deep reinforcement learning have often considered teams as a single agent and valued the teams and players who hold the ball in each discrete event. Then it was challenging to value the actions of multiple players, including players far from the ball, in a spatiotemporally continuous state space. In this paper, we propose a method of valuing possible actions for on- and off-ball soccer players in a single holistic framework based on multi-agent deep reinforcement learning. We consider a discrete action space in a continuous state space that mimics that of Google research football and leverages supervised learning for actions in reinforcement learning. In the experiment, we analyzed the relationships with conventional indicators, season goals, and game ratings by experts, and showed the effectiveness of the proposed method. Our approach can assess how multiple players move continuously throughout the game, which is difficult to be discretized or labeled but vital for teamwork, scouting, and fan engagement.

Abstract: Although there has been significant interest in applying machine learning techniques to structured data, the expressivity (i.e., a description of what can be learned) of such techniques is still poorly understood. In this paper, we study data transformations based on graph neural networks (GNNs). First, we note that the choice of how a dataset is encoded into a numeric form processable by a GNN can obscure the characterisation of a model's expressivity, and we argue that a canonical encoding provides an appropriate basis. Second, we study the expressivity of monotonic max-sum GNNs, which cover a subclass of GNNs with max and sum aggregation functions. We show that, for each such GNN, one can compute a Datalog program such that applying the GNN to any dataset produces the same facts as a single round of application of the program's rules to the dataset. Monotonic max-sum GNNs can sum an unbounded number of feature vectors which can result in arbitrarily large feature values, whereas rule application requires only a bounded number of constants. Hence, our result shows that the unbounded summation of monotonic max-sum GNNs does not increase their expressive power. Third, we sharpen our result to the subclass of monotonic max GNNs, which use only the max aggregation function, and identify a corresponding class of Datalog programs.

Abstract: Multiagent systems deployed in the real world need to cooperate with other agents (including humans) nearly as effectively as these agents cooperate with one another. To design such AI, and provide guarantees of its effectiveness, we need to clearly specify what types of agents our AI must be able to cooperate with. In this work we propose a generic model of socially intelligent agents, which are individually rational learners that are also able to cooperate with one another (in the sense that their joint behavior is Pareto efficient). We define rationality in terms of the regret incurred by each agent over its lifetime, and show how we can construct socially intelligent agents for different forms of regret. We then discuss the implications of this model for the development of "robust" MAS that can cooperate with a wide variety of socially intelligent agents.

Abstract: Many high-performing machine learning models are not interpretable. As they are increasingly used in decision scenarios that can critically affect individuals, it is necessary to develop tools to better understand their outputs. Popular explanation methods include contrastive explanations. However, they suffer several shortcomings, among others an insufficient incorporation of background knowledge, and a lack of interactivity. While (dialogue-like) interactivity is important to better communicate an explanation, background knowledge has the potential to significantly improve their quality, e.g., by adapting the explanation to the needs of the end-user. To close this gap, we present REASONX, an explanation tool based on Constraint Logic Programming (CLP). REASONX provides interactive contrastive explanations that can be augmented by background knowledge, and allows to operate under a setting of under-specified information, leading to increased flexibility in the provided explanations. REASONX computes factual and constrative decision rules, as well as closest constrative examples. It provides explanations for decision trees, which can be the ML models under analysis, or global/local surrogate models of any ML model. While the core part of REASONX is built on CLP, we also provide a program layer that allows to compute the explanations via Python, making the tool accessible to a wider audience. We illustrate the capability of REASONX on a synthetic data set, and on a a well-developed example in the credit domain. In both cases, we can show how REASONX can be flexibly used and tailored to the needs of the user.

Abstract: Rapid developments in artificial intelligence technology have led to unmanned systems replacing human beings in many fields requiring high-precision predictions and decisions. In modern operational environments, all job plans are affected by emergency events such as equipment failures and resource shortages, making a quick resolution critical. The use of unmanned systems to assist decision-making can improve resolution efficiency, but their decision-making is not interpretable and may make the wrong decisions. Current unmanned systems require human supervision and control. Based on this, we propose a collaborative human--machine method for resolving unplanned events using two phases: task filtering and task scheduling. In the task filtering phase, we propose a human--machine collaborative decision-making algorithm for dynamic tasks. The GACRNN model is used to predict the state of the job nodes, locate the key nodes, and generate a machine-predicted resolution task list. A human decision-maker supervises the list in real time and modifies and confirms the machine-predicted list through the human--machine interface. In the task scheduling phase, we propose a scheduling algorithm that integrates human experience constraints. The steps to resolve an event are inserted into the normal job sequence to schedule the resolution. We propose several human--machine collaboration methods in each phase to generate steps to resolve an unplanned event while minimizing the impact on the original job plan.

Abstract: Is it possible to evaluate the moral cognition of complex artificial agents? In this work, we take a look at one aspect of morality: `doing the right thing for the right reasons.' We propose a behavior-based analysis of artificial moral cognition which could also be applied to humans to facilitate like-for-like comparison. Morally-motivated behavior should persist despite mounting cost; by measuring an agent's sensitivity to this cost, we gain deeper insight into underlying motivations. We apply this evaluation to a particular set of deep reinforcement learning agents, trained by memory-based meta-reinforcement learning. Our results indicate that agents trained with a reward function that includes other-regarding preferences perform helping behavior in a way that is less sensitive to increasing cost than agents trained with more self-interested preferences.

Abstract: Path of Destruction (PoD) is a self-supervised method for learning iterative generators. The core idea is to produce a training set by destroying a set of artifacts, and for each destructive step create a training instance based on the corresponding repair action. A generator trained on this dataset can then generate new artifacts by ``repairing'' from arbitrary states. The PoD method is very data-efficient in terms of original training examples and well-suited to functional artifacts composed of categorical data, such as game levels and discrete 3D structures. In this paper, we extend the Path of Destruction method to allow designer control over aspects of the generated artifacts. Controllability is introduced by adding conditional inputs to the state-action pairs that make up the repair trajectories. We test the controllable PoD method in a 2D dungeon setting, as well as in the domain of small 3D Lego cars.