Related papers: Carle's Game: An Open-Ended Challenge in Explorato…

Modern video games are becoming richer and more complex in terms of game mechanics. This complexity allows for the emergence of a wide variety of ways to play the game across the players. From the point of view of the game designer, this…

We introduce the Continuous Arcade Learning Environment (CALE), an extension of the well-known Arcade Learning Environment (ALE) [Bellemare et al., 2013]. The CALE uses the same underlying emulator of the Atari 2600 gaming system (Stella),…

While Reinforcement Learning has made great strides towards solving ever more complicated tasks, many algorithms are still brittle to even slight changes in their environment. This is a limiting factor for real-world applications of RL.…

Video games can be used as an excellent test bed for Artificial Intelligence (AI) techniques. They are challenging and non-deterministic, this makes it very difficult to write strong AI players. An example of such a video game is Ms.…

We introduce CARLA, an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban driving systems. In addition to open-source code…

Conway's Game of Life is the best-known cellular automaton. It is a classic model of emergence and self-organization, it is Turing-complete, and it can simulate a universal constructor. The Game of Life belongs to the set of semi-totalistic…

This paper describes a new concept of cellular automaton (CA). XCA consists of a set of arcs (edges) that correspond to cells in CA. At a particular time, the arcs are connected to a directed graph. With each time step, the arcs exchange…

The classical "game of life" (GOL) due to Conway is a famous mathematical game constructed as a two-dimensional cellular automaton in which each cell is either alive or dead. A set of evolutionary rules determines whether a cell dies,…

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,…

In this article we introduce the Arcade Learning Environment (ALE): both a challenge problem and a platform and methodology for evaluating the development of general, domain-independent AI technology. ALE provides an interface to hundreds…

Reproduction, development, and individual interactions are essential topics in artificial life. The cellular automata, which can handle these in a composite way, is highly restricted in its form and behavior because it represents life as a…

Cellular automata (CA) captivate researchers due to teh emergent, complex individualized behavior that simple global rules of interaction enact. Recent advances in the field have combined CA with convolutional neural networks to achieve…

Motion synthesis in a dynamic environment has been a long-standing problem for character animation. Methods using motion capture data tend to scale poorly in complex environments because of their larger capturing and labeling requirement.…

The increasing complexity of gameplay mechanisms in modern video games is leading to the emergence of a wider range of ways to play games. The variety of possible play-styles needs to be anticipated by designers, through automated tests.…

Autonomous-driving research has recently embraced deep Reinforcement Learning (RL) as a promising framework for data-driven decision making, yet a clear picture of how these algorithms are currently employed, benchmarked and evaluated is…

Creatures in the real world constantly encounter new and diverse challenges they have never seen before. They will often need to adapt to some of these tasks and solve them in order to survive. This almost endless world of novel challenges…

Can we quantify the change of complexity throughout evolutionary processes? We attempt to address this question through an empirical approach. In very general terms, we simulate two simple organisms on a computer that compete over limited…

Agents capable of accomplishing complex tasks through multiple interactions with the environment have emerged as a popular research direction. However, in such multi-step settings, the conventional group-level policy optimization algorithm…

Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation. Existing methods still rely heavily on fixed heuristics and hard-coded…

Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is hazardous, imperiling the RL agent, other agents, and the environment. To overcome this difficulty, we propose a "safety-critical adaptation"…