No abstract

These methods learn to amplify terrain details by using an exemplar of highresolution detailed terrains to transfer the theme. In this paper, we propose Generative Adversarial Terrain Amplication (GATA) that achieves better local/global coherence compared to the existing data-driven methods while providing even more ways to control the theme. GATA is comprised of two key ingredients. The rst one is a novel embedding of themes into vectors of real numbers to achieve a single tool for multi-theme amplication. The theme component can leverage existing LIDAR data to generate similar terrain features. It can also generate new ctional themes by tuning the embedding vector or even encoding a new example terrain into an embedding. The second one is an adversarially trained model that, conditioned on an embedding and a low-resolution terrain, generates a high-resolution terrain adhering to the desired theme. The proposed integral approach reduces the need for unnecessary manual adjustments, can speed up the development, and brings the model quality to a new level. Our implementation of the proposed method has proved successful in large-scale terrain authoring for an open-world game. CCS Concepts: • Computing methodologies → Neural networks; Learning latent representations; Shape modeling;

Human players in professional team sports achieve high level coordination by dynamically choosing complementary skills and executing primitive actions to perform these skills. As a step toward creating intelligent agents with this capability for fully cooperative multi-agent settings, we propose a two-level hierarchical multiagent reinforcement learning (MARL) algorithm with unsupervised skill discovery. Agents learn useful and distinct skills at the low level via independent Q-learning, while they learn to select complementary latent skill variables at the high level via centralized multiagent training with an extrinsic team reward. The set of low-level skills emerges from an intrinsic reward that solely promotes the decodability of latent skill variables from the trajectory of a low-level skill, without the need for hand-crafted rewards for each skill. For scalable decentralized execution, each agent independently chooses latent skill variables and primitive actions based on local observations. Our overall method enables the use of general cooperative MARL algorithms for training high level policies and single-agent RL for training low level skills. Experiments on a stochastic high dimensional team game show the emergence of useful skills and cooperative team play. The interpretability of the learned skills show the promise of the proposed method for achieving human-AI cooperation in team sports games.

No abstract

Recently, there have been several high-profile achievements of agents learning to play games against humans and beat them. In this paper, we study the problem of training intelligent agents in service of game development. Unlike the agents built to "beat the game", our agents aim to produce human-like behavior to help with game evaluation and balancing. We discuss two fundamental metrics based on which we measure the human-likeness of agents, namely skill and style, which are multi-faceted concepts with practical implications outlined in this paper. We report four case studies in which the style and skill requirements inform the choice of algorithms and metrics used to train agents; ranging from A* search to state-of-the-art deep reinforcement learning. We, further, show that the learning potential of state-of-the-art deep RL models does not seamlessly transfer from the benchmark environments to target ones without heavily tuning their hyperparameters, leading to linear scaling of the engineering efforts and computational cost with the number of target domains.