Related papers: MazeBase: A Sandbox for Learning from Games

We present a novel modular architecture for StarCraft II AI. The architecture splits responsibilities between multiple modules that each control one aspect of the game, such as build-order selection or tactics. A centralized scheduler…

Humans have an impressive ability to solve complex coordination problems in a fully distributed manner. This ability, if learned as a set of distributed multirobot coordination strategies, can enable programming large groups of robots to…

Vision-Language Models (VLMs) have demonstrated exceptional general reasoning capabilities. However, their performance in embodied navigation remains hindered by a scarcity of aligned open-world vision and robot control data. Despite…

Recent work in deep reinforcement learning has allowed algorithms to learn complex tasks such as Atari 2600 games just from the reward provided by the game, but these algorithms presently require millions of training steps in order to…

To solve a text-based game, an agent needs to formulate valid text commands for a given context and find the ones that lead to success. Recent attempts at solving text-based games with deep reinforcement learning have focused on the latter,…

This paper introduces a surrogate model of gameplay that learns the mapping between different game facets, and applies it to a generative system which designs new content in one of these facets. Focusing on the shooter game genre, the paper…

The incredible feats of athleticism demonstrated by humans are made possible in part by a vast repertoire of general-purpose motor skills, acquired through years of practice and experience. These skills not only enable humans to perform…

To make AI systems broadly useful for challenging real-world tasks, we need them to learn complex human goals and preferences. One approach to specifying complex goals asks humans to judge during training which agent behaviors are safe and…

We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle…

Large language models (LLMs) excel at many supervised tasks but often struggle with structured reasoning in unfamiliar settings. This discrepancy suggests that standard fine-tuning pipelines may instill narrow, domain-specific heuristics…

Real-world data collection for embodied agents remains costly and unsafe, calling for scalable, realistic, and simulator-ready 3D environments. However, existing scene-generation systems often rely on rule-based or task-specific pipelines,…

Going from research to production, especially for large and complex software systems, is fundamentally a hard problem. In large-scale game production, one of the main reasons is that the development environment can be very different from…

Deception is a technique to mislead human or computer systems by manipulating beliefs and information. For the applications of cyber deception, non-cooperative games become a natural choice of models to capture the adversarial interactions…

We formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games. We propose to employ encoder-decoder neural networks for this task, and…

Natural behavior consists of dynamics that are complex and unpredictable, especially when trying to predict many steps into the future. While some success has been found in building representations of behavior under constrained or…

Adversarial training, a special case of multi-objective optimization, is an increasingly prevalent machine learning technique: some of its most notable applications include GAN-based generative modeling and self-play techniques in…

Logical rules are a popular knowledge representation language in many domains, representing background knowledge and encoding information that can be derived from given facts in a compact form. However, rule formulation is a complex process…

Reinforcement learning agents have traditionally been evaluated on small toy problems. With advances in computing power and the advent of the Arcade Learning Environment, it is now possible to evaluate algorithms on diverse and difficult…

A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models. We show that carefully designed generative models that learn and operate on compact state…

Large Language Models (LLMs) are rapidly saturating existing benchmarks, necessitating new open-ended evaluations. We introduce the Factorio Learning Environment (FLE), based on the game of Factorio, that tests agents in long-term planning,…