相关论文: Carle's Game: An Open-Ended Challenge in Explorato…

Realistic manipulation tasks require a robot to interact with an environment with a prolonged sequence of motor actions. While deep reinforcement learning methods have recently emerged as a promising paradigm for automating manipulation…

Automated game design (AGD), the study of automatically generating game rules, has a long history in technical games research. AGD approaches generally rely on approximations of human play, either objective functions or AI agents. Despite…

Mixed cooperative-competitive control scenarios such as human-machine interaction with individual goals of the interacting partners are very challenging for reinforcement learning agents. In order to contribute towards intuitive…

As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can (1) learn by themselves continually in a self-motivated and self-initiated manner rather than being…

Recently testing of games via autonomous agents has shown great promise in tackling challenges faced by the game industry, which mainly relied on either manual testing or record/replay. In particular Reinforcement Learning (RL) solutions…

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…

Cellular automata have long been celebrated for their ability to generate complex behaviors from simple, local rules, with well-known discrete models like Conway's Game of Life proven capable of universal computation. Recent advancements…

Multi-agent reinforcement learning (MARL) is a widely used Artificial Intelligence (AI) technique. However, current studies and applications need to address its scalability, non-stationarity, and trustworthiness. This paper aims to review…

This paper surveys the emerging science of how to design a ``COllective INtelligence'' (COIN). A COIN is a large multi-agent system where: (i) There is little to no centralized communication or control; and (ii) There is a provided world…

Recently there have been multiple calls for curricular reforms to develop new pathways to the science, technology, engineering and math (STEM) disciplines. The Marble Game answers these calls by providing a conceptual framework for…

Complex systems are ubiquitous in the real world and tend to have complicated and poorly understood dynamics. For their control issues, the challenge is to guarantee accuracy, robustness, and generalization in such bloated and troubled…

The convergence of low-altitude economies, embodied intelligence, and air-ground cooperative systems creates growing demand for simulation infrastructure capable of jointly modeling aerial and ground agents within a single physically…

Zero-shot coordination in cooperative artificial intelligence (AI) remains a significant challenge, which means effectively coordinating with a wide range of unseen partners. Previous algorithms have attempted to address this challenge by…

JADE is an educational game we have imagined, designed, built, and used successfully in various contexts. This board game enables learning and practicing software ergonomics concepts. It is intended for beginners. We use it every year…

Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity. As such, game agents offer a valuable testbed for exploring capabilities relevant to Artificial General Intelligence. Recently, the…

Reinforcement Learning (RL) has emerged as a powerful paradigm in Artificial Intelligence (AI), enabling agents to learn optimal behaviors through interactions with their environments. Drawing from the foundations of trial and error, RL…

Reinforcement Learning (RL) agents have great successes in solving tasks with large observation and action spaces from limited feedback. Still, training the agents is data-intensive and there are no guarantees that the learned behavior is…

Despite groundbreaking progress in reinforcement learning for robotics, gameplay, and other complex domains, major challenges remain in applying reinforcement learning to the evolving, open-world problems often found in critical application…

Recent advances in artificial intelligence have been strongly driven by the use of game environments for training and evaluating agents. Games are often accessible and versatile, with well-defined state-transitions and goals allowing for…

Cellular automata (CA) have been utilized for decades as discrete models of many physical, mathematical, chemical, biological, and computing systems. The most widely known form of CA, the elementary cellular automaton (ECA), has been…