paper-with-me

홈 › Papers

Human-Centric Goal Reasoning with Ripple-Down Rules

2024-01-30 · Kenji Brameld, Germán Castro, Claude Sammut, Mark Roberts, David W. Aha

ActorSim is a goal reasoning framework developed at the Naval Research Laboratory. Originally, all goal reasoning rules were hand-crafted. This work extends ActorSim with the capability of learning by demonstration, that is, when a human trainer disagrees with a decision made by the system, the trainer can take over and show the system the correct decision. The learning component uses Ripple-Down Rules (RDR) to build new decision rules to correctly handle similar cases in the future. The system is demonstrated using the RoboCup Rescue Agent Simulation, which simulates a city-wide disaster, requiring emergency services, including fire, ambulance and police, to be dispatched to different sites to evacuate civilians from dangerous situations. The RDRs are implemented in a scripting language, FrameScript, which is used to mediate between ActorSim and the agent simulator. Using Ripple-Down Rules, ActorSim can scale to an order of magnitude more goals than the previous version.

📄 PDF Abstract BibTeX arXiv:2402.10224

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

RippleMem: From Isolated Retrieval to Associative Recollection for Long-Term Agent Memory

2026-08-13 · Jingbo Ji, Lingyi Li, Xilong Cheng, Yuhao Zhou 외 arxiv

LLM-based agents increasingly rely on external memory to support long-horizon reasoning and interaction. However, the main bottleneck is not simply storing past experience, but recovering the right set of evidence when r…

EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videos

2025-03-28 · YuXuan Li, Vijay Veerabadran, Michael L. Iuzzolino, Brett D. Roads 외

We introduce EgoToM, a new video question-answering benchmark that extends Theory-of-Mind (ToM) evaluation to egocentric domains. Using a causal ToM model, we generate multi-choice video QA instances for the Ego4D datase…

BenchmarkingQuestion AnsweringVideo Question Answering

EgoTaskQA: Understanding Human Tasks in Egocentric Videos

2022-10-08 · Baoxiong Jia, Ting Lei, Song-Chun Zhu, Siyuan Huang

Understanding human tasks through video observations is an essential capability of intelligent agents. The challenges of such capability lie in the difficulty of generating a detailed understanding of situated actions, t…

Action LocalizationcounterfactualDescriptiveDiagnostic+3

RDRPOSTagger: A Ripple Down Rules-based Part-Of-Speech Tagger

2014-04-01 · EACL 2014 4 · Dat Quoc Nguyen, Dai Quoc Nguyen, Dang Duc Pham, Son Bao Pham
Part-Of-Speech Tagging

Personality-aware Human-centric Multimodal Reasoning: A New Task, Dataset and Baselines

2023-04-05 · Yaochen Zhu, Xiangqing Shen, Rui Xia

Personality traits, emotions, and beliefs shape individuals' behavioral choices and decision-making processes. However, for one thing, the affective computing community normally focused on predicting personality traits b…

Decision MakingMultimodal Reasoning