Prior work on generating explanations in a planning and decision-making context has focused on providing the rationale behind an AI agent's decision making. While these methods provide the right explanations from the explainer's perspective, they fail to heed the cognitive requirement of understanding an explanation from the explainee's (the human's) perspective. In this work, we set out to address this issue by first considering the influence of information order in an explanation, or the progressiveness of explanations. Intuitively, progression builds later concepts on previous ones and is known to contribute to better learning. In this work, we aim to investigate similar effects during explanation generation when an explanation is broken into multiple parts that are communicated sequentially. The challenge here lies in modeling the humans' preferences for information order in receiving such explanations to assist understanding. Given this sequential process, a formulation based on goal-based MDP for generating progressive explanations is presented. The reward function of this MDP is learned via inverse reinforcement learning based on explanations that are retrieved via human subject studies. We first evaluated our approach on a scavenger-hunt domain to demonstrate its effectively in capturing the humans' preferences. Upon analyzing the results, it revealed something more fundamental: the preferences arise strongly from both domain dependent and independence features. The correlation with domain independent features pushed us to verify this result further in an escape room domain. Results confirmed our hypothesis that the process of understanding an explanation was a dynamic process. The human preference that reflected this aspect corresponded exactly to the progression for knowledge assimilation hidden deeper in our cognitive process.
School of Computing, Informatics and Decision Systems Engineering, Arizona State University（亚利桑那州立大学计算、信息与决策系统工程学院）
Providing explanations is considered an imperative ability for an AI agent in a human-robot teaming framework. The right explanation provides the rationale behind an AI agent's decision-making. However, to maintain the human teammate's cognitive demand to comprehend the provided explanations, prior works have focused on providing explanations in a specific order or intertwining the explanation generation with plan execution. Moreover, these approaches do not consider the degree of details required to share throughout the provided explanations. In this work, we argue that the agent-generated ex…
Computer Science and Engineering Department at Arizona State University（亚利桑那州立大学计算机科学与工程系）
Generating explanation to explain its behavior is an essential capability for a robotic teammate. Explanations help human partners better understand the situation and maintain trust of their teammates. Prior work on robot generating explanations focuses on providing the reasoning behind its decision making. These approaches, however, fail to heed the cognitive requirement of understanding an explanation. In other words, while they provide the right explanations from the explainer's perspective, the explainee part of the equation is ignored. In this work, we address an important aspect along th…
Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）；Nanyang Technological University（南洋理工大学）；Peng Cheng Laboratory（鹏城实验室）
Stanford University（斯坦福大学）；University of Colorado Boulder（科罗拉多大学博尔德分校）
Online solvers for partially observable Markov decision processes have difficulty scaling to problems with large action spaces. Monte Carlo tree search with progressive widening attempts to improve scaling by sampling from the action space to construct a policy search tree. The performance of progressive widening search is dependent upon the action sampling policy, often requiring problem-specific samplers. In this work, we present a general method for efficient action sampling based on Bayesian optimization. The proposed method uses a Gaussian process to model a belief over the action-value f…
Rather than augmenting rewards with penalties for undesired behavior, Constrained Partially Observable Markov Decision Processes (CPOMDPs) plan safely by imposing inviolable hard constraint value budgets. Previous work performing online planning for CPOMDPs has only been applied to discrete action and observation spaces. In this work, we propose algorithms for online CPOMDP planning for continuous state, action, and observation spaces by combining dual ascent with progressive widening. We empirically compare the effectiveness of our proposed algorithms on continuous CPOMDPs that model both toy…
In this paper, we consider planning in stochastic shortest path (SSP) problems, a subclass of Markov Decision Problems (MDP). We focus on medium-size problems whose state space can be fully enumerated. This problem has numerous important applications, such as navigation and planning under uncertainty. We propose a new approach for constructing a multi-level hierarchy of progressively simpler abstractions of the original problem. Once computed, the hierarchy can be used to speed up planning by first finding a policy for the most abstract level and then recursively refining it into a solution to…
University of California, Berkeley（加州大学伯克利分校）；University of Colorado Boulder（科罗拉多大学博尔德分校）
This paper introduces Voronoi Progressive Widening (VPW), a generalization of Voronoi optimistic optimization (VOO) and action progressive widening to partially observable Markov decision processes (POMDPs). Tree search algorithms can use VPW to effectively handle continuous or hybrid action spaces by efficiently balancing local and global action searching. This paper proposes two VPW-based algorithms and analyzes them from theoretical and simulation perspectives. Voronoi Optimistic Weighted Sparse Sampling (VOWSS) is a theoretical tool that justifies VPW-based online solvers, and it is the fi…
Microsoft Research（微软研究院）；IBM Research AI（IBM人工智能研究院）；Singapore Management University（新加坡管理大学）
We propose a framework, called neural-progressive hedging (NP), that leverages stochastic programming during the online phase of executing a reinforcement learning (RL) policy. The goal is to ensure feasibility with respect to constraints and risk-based objectives such as conditional value-at-risk (CVaR) during the execution of the policy, using probabilistic models of the state transitions to guide policy adjustments. The framework is particularly amenable to the class of sequential resource allocation problems since feasibility with respect to typical resource constraints cannot be enforced …
Intelligent robots are redefining a multitude of critical domains but are still far from being fully capable of assisting human peers in day-to-day tasks. An important requirement of collaboration is for each teammate to maintain and respect an understanding of the others' expectations of itself. Lack of which may lead to serious issues such as loose coordination between teammates, reduced situation awareness, and ultimately teaming failures. Hence, it is important for robots to behave explicably by meeting the human's expectations. One of the challenges here is that the expectations of the hu…
Human-robot interaction can be divided into two categories based on the physical distance between the human and robot: remote and proximal. In proximal interaction, the human and robot often engage in close coordination; in remote interaction, the human and robot are less coupled due to communication constraints. As a result, providing automation for the robot in remote interaction becomes more important. Thus far, human factor studies on automation in remote human-robot interaction have been restricted to various forms of supervision, in which the robot is essentially being used as a smart mo…
Center for Research on Intelligent System and Engineering（智能系统与工程研究中心）；Institute of Automation, CAS（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Model-based reinforcement learning (MBRL) is believed to have higher sample efficiency compared with model-free reinforcement learning (MFRL). However, MBRL is plagued by dynamics bottleneck dilemma. Dynamics bottleneck dilemma is the phenomenon that the performance of the algorithm falls into the local optimum instead of increasing when the interaction step with the environment increases, which means more data can not bring better performance. In this paper, we find that the trajectory reward estimation error is the main reason that causes dynamics bottleneck dilemma through theoretical analy…
Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning
State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院通用人工智能国家重点实验室）；Amazon AGI SF Lab（亚马逊AGI旧金山实验室）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）
New Insights into Automatic Treatment Planning for Cancer Radiotherapy Using Explainable Artificial Intelligence
Department of Physics, The University of Texas at Arlington（德克萨斯大学阿灵顿分校物理系）；Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University（约翰霍普金斯大学放射肿瘤学与分子放射科学系）
Multi-Robot Open Adaptive Teaming Across Unseen Environments, Partners, and Scales
Shanghai Jiao Tong University（上海交通大学）；Sun Yat-sen University（中山大学）；National University of Singapore（新加坡国立大学）；Genisom AI；University of Bristol（布里斯托大学）；Purdue University（普渡大学）；Newcastle University（新castle大学）
Often, when modeling human decision-making behaviors in the context of human-robot teaming, the emotion aspect of human is ignored. Nevertheless, the influence of emotion, in some cases, is not only undeniable but beneficial. This work studies the human-like characteristics brought by regret emotion in one-human-multi-robot teaming for the application of domain search. In such application, the task management load is outsourced to the robots to reduce the human's workload, freeing the human to do more important work. The regret decision model is first used by each robot for deciding whether to…
PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly
Mohamed bin Zayed University of Artificial Intelligence（莫扎德·本·扎耶德人工智能大学）；Tsinghua Shenzhen International Graduate School, Tsinghua University, China（清华大学深圳国际研究生院）；Shenzhen Campus of Sun Yat-sen University（孙中山大学深圳校区）；Spatialtemporal AI（时空人工智能）；Shanghai Jiao Tong University（上海交通大学）
An LLM-based Framework for Human-Swarm Teaming Cognition in Disaster Search and Rescue
School of Electronics and Information, Northwestern Polytechnical University（电子工程学院，西北工业大学）；Chongqing Institute for Brain and Intelligence, Guangyang Bay Laboratory（脑科学与智能研究院，广阳湾实验室）
MINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active Elicitation
Department of Electrical and Computer Engineering, George Washington University（乔治华盛顿大学电气与计算机工程系）；Department of Electrical and Computer Engineering, Northeastern University（东北大学电气与计算机工程系）
IBM T. J. Watson Research Center（IBM T. J. 沃森研究中心）
In this paper, we introduce the problem of denoting and deriving the complexity of workflows (plans, schedules) in collaborative, planner-assisted settings where humans and agents are trying to jointly solve a task. The interactions -- and hence the workflows that connect the human and the agents -- may differ according to the domain and the kind of agents. We adapt insights from prior work in human-agent teaming and workflow analysis to suggest metrics for workflow complexity. The main motivation behind this work is to highlight metrics for human comprehensibility of plans and schedules. The …
University of Science and Technology of China（中国科学技术大学）
One of the challenges of task planning is to find out what causes the planning failure and how to handle the failure intelligently. This paper shows how to achieve this. The idea is inspired by the connected graph: each verticle represents a set of compatible \textit{states}, and each edge represents an \textit{action}. For any given initial states and goals, we construct virtual actions to ensure that we always get a plan via task planning. This paper shows how to introduce virtual action to extend action models to make the graph to be connected: i) explicitly defines static predicate (type, …
Computer Science Department, Arizona State University（亚利桑那州立大学计算机科学系）；IBM T. J. Watson Research Center（IBM T.J.沃森研究中心）
In this paper, we report on the visualization capabilities of an Explainable AI Planning (XAIP) agent that can support human in the loop decision making. Imposing transparency and explainability requirements on such agents is especially important in order to establish trust and common ground with the end-to-end automated planning system. Visualizing the agent's internal decision-making processes is a crucial step towards achieving this. This may include externalizing the "brain" of the agent -- starting from its sensory inputs, to progressively higher order decisions made by it in order to dri…
Context Matters! Relaxing Goals with LLMs for Feasible 3D Scene Planning
Department of Computer, Automation and Management Engineering, Sapienza University of Rome（Sapienza大学计算机、自动化与管理工程系）；Department of Electronics and Automation, Mohamed Khider University of Biskra（Mohamed Khider大学电子与自动化系）；International University of Rome UNINT, Rome（罗马国际大学UNINT）
Structured Preference Optimization for Vision-Language Long-Horizon Task Planning
Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）；The Chinese University of Hong Kong（香港中文大学）；Spatialtemporal AI（时空人工智能）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；The University of Hong Kong（香港大学）；Shanghai Jiaotong University（上海交通大学）
