- author = "K. Ege {de Bruin}",
- title = "Software review: {EvoGym}",
- journal = "Genetic Programming and Evolvable Machines",
- year = "2026",
- volume = "27",
- pages = "Article no 16",
- month = "31 " # jul,
- keywords = "genetic algorithms, genetic programming, Embodied AI, 2D Physics simulation, Reinforcement learning, Evolutionary computation",
- ISSN = "1389-2576",
-
URL = "
https://rdcu.be/fxNHq",
-
DOI = "
10.1007/s10710-026-09540-1",
-
video_url = "https://media.springernature.com/original/springer-static/esm/art%3A10.1007%2Fs10710-026-09540-1/MediaObjects/10710_2026_9540_MOESM1_ESM.gif",
- size = "4 pages",
- abstract = "EvoGym is a lightweight Python framework for simulating voxel-based robots in two-dimensional environments. We describe the simulator's core features, including its Gymnasium-compatible API, diverse benchmark tasks, and flexible tools for designing custom environments. The review highlights EvoGym's accessibility, computational efficiency, and suitability for research and education in evolutionary robotics and reinforcement learning. Overall, EvoGym is a practical platform for research and education in embodied AI.",
-
notes = "https://evolutiongym.github.io/
University of Oslo",
