This paper explores successor features for knowledge transfer in zero-sum, complete-information, and turn-based games. Prior research in single-agent systems has shown that successor features can provide a "jump start" for agents when facing new tasks with varying reward structures. However, knowledge transfer in games typically relies on value and equilibrium transfers, which heavily depends on the similarity between tasks. This reliance can lead to failures when the tasks differ significantly. To address this issue, this paper presents an application of successor features to games and presents a novel algorithm called Game Generalized Policy Improvement (GGPI), designed to address Markov games in multi-agent reinforcement learning. The proposed algorithm enables the transfer of learning values and policies across games. An upper bound of the errors for transfer is derived as a function the similarity of the task. Through experiments with a turn-based pursuer-evader game, we demonstrate that the GGPI algorithm can generate high-reward interactions and one-shot policy transfer. When further tested in a wider set of initial conditions, the GGPI algorithm achieves higher success rates with improved path efficiency compared to those of the baseline algorithms.

Human-Autonomy Teaming (HAT) is a multi-disciplinary domain with a diverse set of research needs and goals stemming from fields such as computer science, robotics, and human factors. This melting pot of fields generates a unique challenge in that there exist many disjoint research methods (measures and tasks) that cause issues with knowledge transfer and comparison between researchers. One way to address this issue is by providing researchers with a testbed containing a standardized suite of analysis tools and tasks that allow direct comparison between different approaches. Therefore, this study attempts to bring the HAT community together in a collaborative discussion to collect and organize their research needs for the future development of these testbeds. Specifically, through thematic analysis, our work reveals three emergent prongs that underpin testbed needs of HAT experts: task, AI, and technical requirements. Also, we organize our thematic analysis by priority to suggest possible paths for HAT testbed development to maximize its immediate and continued utility. Our research indicates that the HAT community places significant importance on both the pre-established, standardized functions available within the testbed and the freedom to tailor and develop their unique tasks or AI solutions.

As humans and robots start to collaborate in close proximity, robots are tasked to perceive, comprehend, and anticipate human partners' actions, which demands a predictive model to describe how humans collaborate with each other in joint actions. Previous studies either simplify the collaborative task as an optimal control problem between two agents or do not consider the learning process of humans during repeated interaction. This idyllic representation is thus not able to model human rationality and the learning process. In this paper, a bounded-rational and game-theoretical human cooperative model is developed to describe the cooperative behaviors of the human dyad. An experiment of a joint object pushing collaborative task was conducted with 30 human subjects using haptic interfaces in a virtual environment. The proposed model uses inverse optimal control (IOC) to model the reward parameters in the collaborative task. The collected data verified the accuracy of the predicted human trajectory generated from the bounded rational model excels the one with a fully rational model. We further provide insight from the conducted experiments about the effects of leadership on the performance of human collaboration.

Human-robot interactions (HRI) can be modeled as differential games with incomplete information, where each agent holds private reward parameters. Due to the open challenge in finding perfect Bayesian equilibria of such games, existing studies often decouple the belief and physical dynamics by iterating between belief update and motion planning. Importantly, the robot’s reward parameters are often assumed to be known to the humans, in order to simplify the computation. We show in this paper that under this simplification, the robot performs non-empathetic belief update about the humans’ parameters, which causes high safety risks in uncontrolled intersection scenarios. In contrast, we propose a model for empathetic belief update, where the agent updates the joint probabilities of all agents’ parameter combinations. The update uses a neural network that approximates the Nash equilibrial action-values of agents. We compare empathetic and non-empathetic belief update methods on a two-vehicle uncontrolled intersection case with short reaction time. Results show that when both agents are unknowingly aggressive (or non-aggressive), empathy is necessary for avoiding collisions when agents have false believes about each others’ parameters. This paper demonstrates the importance of acknowledging the incomplete-information nature of HRI.