Learning, Planning, and Control in a Monolithic Neural Event Inference Architecture
Cognitive Modeling Group Computer Science Department University of Tübingen（图宾根大学认知建模组计算机科学系）
Martin V. Butz, David Bilkey, Dania Humaidan, Alistair Knott, Sebastian Otte
备注：
This is the final revision submitted to the Neural Networks journal. The revision mainly includes improvements in language, explanation, and additional references and system relations
We introduce REPRISE, a REtrospective and PRospective Inference SchEme, which learns temporal event-predictive models of dynamical systems. REPRISE infers the unobservable contextual event state and accompanying temporal predictive models that best explain the recently encountered sensorimotor experiences retrospectively. Meanwhile, it optimizes upcoming motor activities prospectively in a goal-directed manner. Here, REPRISE is implemented by a recurrent neural network (RNN), which learns temporal forward models of the sensorimotor contingencies generated by different simulated dynamic vehicles. The RNN is augmented with contextual neurons, which enable the encoding of distinct, but related, sensorimotor dynamics as compact event codes. We show that REPRISE concurrently learns to separate and approximate the encountered sensorimotor dynamics: it analyzes sensorimotor error signals adapting both internal contextual neural activities and connection weight values. Moreover, we show that REPRISE can exploit the learned model to induce goal-directed, model-predictive control, that is, approximate active inference: Given a goal state, the system imagines a motor command sequence optimizing it with the prospective objective to minimize the distance to the goal. The RNN activities thus continuously imagine the upcoming future and reflect on the recent past, optimizing the predictive model, the hidden neural state activities, and the upcoming motor activities. As a result, event-predictive neural encodings develop, which allow the invocation of highly effective and adaptive goal-directed sensorimotor control.
On Predictive planning and counterfactual learning in active inference
Turner Institute for Brain and Mental Health（特纳脑与心理健康研究所）；School of Psychological Sciences（心理科学学院）；Monash University（莫纳什大学）；IITB-Monash Research Academy（印度理工学院孟买分校-莫纳什大学研究院）；IIT Bombay（印度理工学院孟买分校）；RIKEN Center for Brain Science（理化学研究所脑科学中心）；University College London（伦敦大学学院）；Wellcome Trust Centre for Human Neuroimaging（惠康信托人类神经影像中心）；CIFAR（加拿大高级研究所）
Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference
Department of Statistics and Data Science, UCLA（统计与数据科学系， UCLA）；Salesforce Research（Salesforce 研究）；Akool Research（Akool 研究）；Xi’an Jiaotong University（西安交通大学）；Department of Computer Science, UCLA（计算机科学系， UCLA）
本文提出Latent Plan Transformer（LPT），通过潜在变量推断将规划视为潜在空间推断，从次优轨迹中学习时间一致的抽象并提升长期决策性能。
Joint Task Offloading, Inference Optimization and UAV Trajectory Planning for Generative AI Empowered Intelligent Transportation Digital Twin
Guangxi University Key Laboratory of Intelligent Networking and Scenario System (School of Information and Communication, Guilin University of Electronic Technology)（广西大学智能组网与场景系统重点实验室（桂林电子科技大学信息与通信学院））；Research Institute of Highway Ministry of Transport（交通运输部公路科学研究院）；School of Automation, Guangdong University of Technology（广东工业大学自动化学院）；School of Architecture and Transportation Engineering, Guilin University of Electronic Technology（桂林电子科技大学建筑与交通工程学院）
Turner Institute for Brain and Mental Health, Monash University（莫纳什大学特纳脑与心理健康研究所）；IITB-Monash Research Academy（印度理工学院孟买分校-莫纳什大学研究院）；Department of Electrical Engineering, IIT Bombay（印度理工学院孟买分校电气工程系）；Wellcome Centre for Human Neuroimaging, University College London（伦敦大学学院惠康人类神经影像中心）；Department of Mathematics, Imperial College London（伦敦帝国理工学院数学系）；VERSES Research Lab（VERSES研究实验室）；CIFAR（加拿大高级研究所）
Duke University（杜克大学）；Atom Bioworks（Atom生物工坊）；Mila – Québec AI Institute（魁北克AI研究院）；Université de Montréal（蒙特利尔大学）；The University of Oxford（牛津大学）；Aithyra（Aithyra公司）；University of Pennsylvania（宾夕法尼亚大学）
