arXiv cs.AI· Chaitanya Kaul, Markus Klar, Sebastian Stein, Fraser C. Paterson, John H. Williamson, Roderick Murray-Smith·· 12 小时前AI 评分20
JAXbounce：面向连续控制 Active Inference 的 Pong 类基准
JAXbounce: A Continuous-Control Pong-Like Benchmark for Active Inference Beyond Low Dimensional Environments
AI 导读
JAXbounce 是一个连续控制 Pong 类基准，用于在离散、低维环境之外评估 active inference，支持连续状态、随机动力学以及状态向量或像素网格等可组合观测模型，并可在 JAX 中完全微分和并行化。
正文 · 原文
Abstract:We introduce JAXbounce, a continuous control pong-like benchmark designed to evaluate active inference beyond discrete, low dimensional environments. JAXbounce combines continuous states and stochastic dynamics in discrete time with flexible and composable observation models that allow representing the environment as a state vector or a pixel grid, corruptible through the rich family of noise models we provide. It is fully differentiable and parallelisable in JAX. We run over 10,000 agent simulations on our environment comparing a baseline deterministic solution, to a state-based active inference agent with Unscented Kalman Filter perception and expected free energy planning, and a pixel based agent whose measurement model is a pretrained neural network encoder. All agents are evaluated across three scenarios of increasing difficulty with eight different noise conditions. Our experiments characterise how performance of continuous state agents scales with planning, planning horizons, observation modalities and knowledge of the noise process, exhibiting preference-oriented behaviour even in the presence of increasing uncertainty. We release JAXbounce as a reproducible benchmark for continuous control active inference research.
| Comments: | Published in the Springer CCIS series as part of the 7th International Workshop on Active Inference (IWAI26) |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.28203 [cs.LG] |
| (or arXiv:2610.28203v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28203 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chaitanya Kaul [view email]
[v1]
Tue, 20 Oct 2026 13:43:24 UTC (560 KB)
来源：arXiv cs.AI · arxiv.org