People routinely infer the goals of others by observing their actions over time. Remarkably, we can do so even when those actions lead to failure, enabling us to assist others when we detect that they might not achieve their goals. How might we endow machines with similar capabilities? Here we present an architecture capable of inferring an agent's goals online from both optimal and non-optimal sequences of actions. Our architecture models agents as boundedly-rational planners that interleave search with execution by replanning, thereby accounting for sub-optimal behavior. These models are specified as probabilistic programs, allowing us to represent and perform efficient Bayesian inference over an agent's goals and internal planning processes. To perform such inference, we develop Sequential Inverse Plan Search (SIPS), a sequential Monte Carlo algorithm that exploits the online replanning assumption of these models, limiting computation by incrementally extending inferred plans as new actions are observed. We present experiments showing that this modeling and inference architecture outperforms Bayesian inverse reinforcement learning baselines, accurately inferring goals from both optimal and non-optimal trajectories involving failure and back-tracking, while generalizing across domains with compositional structure and sparse rewards.
MIT Media Lab（麻省理工学院媒体实验室）；Australian National University（澳大利亚国立大学）；Tel-Aviv University（特拉维夫大学）；MIT（麻省理工学院）
Collective intelligence is believed to underly the remarkable success of human society. The formation of accurate shared beliefs is one of the key components of human collective intelligence. How are accurate shared beliefs formed in groups of fallible individuals? Answering this question requires a multiscale analysis. We must understand both the individual decision mechanisms people use, and the properties and dynamics of those mechanisms in the aggregate. As of yet, mathematical tools for such an approach have been lacking. To address this gap, we introduce a new analytical framework: We pr…
When inferring the goals that others are trying to achieve, people intuitively understand that others might make mistakes along the way. This is crucial for activities such as teaching, offering assistance, and deciding between blame or forgiveness. However, Bayesian models of theory of mind have generally not accounted for these mistakes, instead modeling agents as mostly optimal in achieving their goals. As a result, they are unable to explain phenomena like locking oneself out of one's house, or losing a game of chess. Here, we extend the Bayesian Theory of Mind framework to model boundedly…
Principal-Agent (PA) problems describe a broad class of economic relationships characterized by misaligned incentives and asymmetric information. The Principal's problem is to find optimal incentives given the available information, e.g., a manager setting optimal wages for its employees. Whereas the Principal is often assumed rational, comparatively little is known about solutions when the Principal is boundedly rational, especially in the sequential setting, with multiple Agents, and with multiple information channels. Here, we develop RIRL, a deep reinforcement learning framework that solve…
End-users' trust in automated agents is important as automated decision-making and planning is increasingly used in many aspects of people's lives. In real-world applications of planning, multiple optimization objectives are often involved. Thus, planning agents' decisions can involve complex tradeoffs among competing objectives. It can be difficult for the end-users to understand why an agent decides on a particular planning solution on the basis of its objective values. As a result, the users may not know whether the agent is making the right decisions, and may lack trust in it. In this work…
Brown University（布朗大学）；Carnegie Mellon University（卡内基梅隆大学）
We formalize the problem of selecting the optimal set of options for planning as that of computing the smallest set of options so that planning converges in less than a given maximum of value-iteration passes. We first show that the problem is NP-hard, even if the task is constrained to be deterministic---the first such complexity result for option discovery. We then present the first polynomial-time boundedly suboptimal approximation algorithm for this setting, and empirically evaluate it against both the optimal options and a representative collection of heuristic approaches in simple grid-b…
Future of Humanity Institute（人类未来研究所）；University of Oxford（牛津大学）；Vector Institute（向量研究所）；University of Toronto（多伦多大学）；Machine Intelligence Research Institute（机器智能研究所）
Inverse reinforcement learning (IRL) attempts to infer human rewards or preferences from observed behavior. Since human planning systematically deviates from rationality, several approaches have been tried to account for specific human shortcomings. However, the general problem of inferring the reward function of an agent of unknown rationality has received little attention. Unlike the well-known ambiguity problems in IRL, this one is practically relevant but cannot be resolved by observing the agent's policy in enough environments. This paper shows (1) that a No Free Lunch result implies it i…
College of System Engineering, National University of Defense Technology（国防科技大学系统工程学院）
In this paper, we present a hierarchical path planning framework called SG-RL (subgoal graphs-reinforcement learning), to plan rational paths for agents maneuvering in continuous and uncertain environments. By "rational", we mean (1) efficient path planning to eliminate first-move lags; (2) collision-free and smooth for agents with kinematic constraints satisfied. SG-RL works in a two-level manner. At the first level, SG-RL uses a geometric path-planning method, i.e., Simple Subgoal Graphs (SSG), to efficiently find optimal abstract paths, also called subgoal sequences. At the second level, SG…
Pedestrian crossing decisions can be explained by bounded optimal decision-making under noisy visual perception
Institute for Transport Studies, University of Leeds（利兹大学交通研究院）；Faculty of Information Technology, University of Jyväskylä（于韦斯屈莱大学信息技术学院）；Aalto University（阿尔托大学）
Learning Top-k Subtask Planning Tree based on Discriminative Representation Pre-training for Decision Making
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Future Technology, University of Chinese Academy of Sciences（中国科学院大学未来技术学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
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…
University of Pennsylvania（宾夕法尼亚大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Max Planck Institute for Biological Cybernetics（马克斯·普朗克生物控制论研究所）；Google Inc.（谷歌公司）；Korea Advanced Institute of Science and Technology（韩国高等科学技术研究院）；The Hebrew University（希伯来大学）
The aim of this work is to address the question of whether we can in principle design rational decision-making agents or artificial intelligences embedded in computable physics such that their decisions are optimal in reasonable mathematical senses. Recent developments in rare event probability estimation, recursive bayesian inference, neural networks, and probabilistic planning are sufficient to explicitly approximate reinforcement learners of the AIXI style with non-trivial model classes (here, the class of resource-bounded Turing machines). Consideration of the effects of resource limitatio…
LARC: Towards Human-level Constrained Retrosynthesis Planning through an Agentic Framework
Department of Computer Science and Engineering, 2 Division of Medicinal Chemistry & Pharmacognosy, 3 Department of Biomedical Informatics, 4 Translational Data Analytics Institute（1 计算机科学与工程系，2 药物化学与药理学系，3 生物医学信息学系，4 转化数据分析研究所）
A key challenge in non-cooperative multi-agent systems is that of developing efficient planning algorithms for intelligent agents to interact and perform effectively among boundedly rational, self-interested agents (e.g., humans). The practicality of existing works addressing this challenge is being undermined due to either the restrictive assumptions of the other agents' behavior, the failure in accounting for their rationality, or the prohibitively expensive cost of modeling and predicting their intentions. To boost the practicality of research in this field, we investigate how intention pre…
Rice University（莱斯大学）；University of Minnesota（明尼苏达大学）；Baylor College of Medicine（贝勒医学院）
Continuous control and planning remains a major challenge in robotics and machine learning. Neuroscience offers the possibility of learning from animal brains that implement highly successful controllers, but it is unclear how to relate an animal's behavior to control principles. Animals may not always act optimally from the perspective of an external observer, but may still act rationally: we hypothesize that animals choose actions with highest expected future subjective value according to their own internal model of the world. Their actions thus result from solving a different optimal contro…
Princeton Neuroscience Institute, Princeton University（普林斯顿大学普林斯顿神经科学研究所）；Department of Psychology, Princeton University（普林斯顿大学心理学系）
People often plan hierarchically. That is, rather than planning over a monolithic representation of a task, they decompose the task into simpler subtasks and then plan to accomplish those. Although much work explores how people decompose tasks, there is less analysis of why people decompose tasks in the way they do. Here, we address this question by formalizing task decomposition as a resource-rational representation problem. Specifically, we propose that people decompose tasks in a manner that facilitates efficient use of limited cognitive resources given the structure of the environment and …
An important feature of pervasive, intelligent assistance systems is the ability to dynamically adapt to the current needs of their users. Hence, it is critical for such systems to be able to recognize those goals and needs based on observations of the user's actions and state of the environment. In this work, we investigate the application of two state-of-the-art, planning-based plan recognition approaches in a real-world setting. So far, these approaches were only evaluated in artificial settings in combination with agents that act perfectly rational. We show that such approaches have diffic…
Technion - Israel Institute of Technology（以色列理工学院）
In many real-world planning problems, action's impact differs with a place, time and the context in which the action is applied. The same action with the same effects in a different context or states can cause a different change. In actions with incomplete precondition list, that applicable in several states and circumstances, ambiguity regarding the impact of the action is challenging even in small domains. To estimate the real impact of actions, an evaluation of the effect list will not be enough; a relative estimation is more informative and suitable for estimation of action's real impact. …
The Graduate University for Advanced Studies (Sokendai)（综合研究大学院大学（Sokendai））；National Institute of Informatics（国立信息学研究所）
A recent approach based on Bayesian inverse planning for the "theory of mind" has shown good performance in modeling human cognition. However, perfect inverse planning differs from human cognition during one kind of complex tasks due to human bounded rationality. One example is an environment in which there are many available plans for achieving a specific goal. We propose a "plan predictability oriented model" as a model of inferring other peoples' goals in complex environments. This model adds the bias that people prefer predictable plans. This bias is calculated with simple plan prediction.…
Czech Technical University in Prague（布拉格捷克理工大学）；The University of Edinburgh（爱丁堡大学）
Travel sharing, i.e., the problem of finding parts of routes which can be shared by several travellers with different points of departure and destinations, is a complex multiagent problem that requires taking into account individual agents' preferences to come up with mutually acceptable joint plans. In this paper, we apply state-of-the-art planning techniques to real-world public transportation data to evaluate the feasibility of multiagent planning techniques in this domain. The potential application value of improving travel sharing technology has great application value due to its ability …
Massachusetts Institute of Technology（麻省理工学院）；Stanford University（斯坦福大学）
We present a framework for learning useful subgoals that support efficient long-term planning to achieve novel goals. At the core of our framework is a collection of rational subgoals (RSGs), which are essentially binary classifiers over the environmental states. RSGs can be learned from weakly-annotated data, in the form of unsegmented demonstration trajectories, paired with abstract task descriptions, which are composed of terms initially unknown to the agent (e.g., collect-wood then craft-boat then go-across-river). Our framework also discovers dependencies between RSGs, e.g., the task coll…
MIND: Multi-agent inference for negotiation dialogue in travel planning
School of Mechanical Engineering, Sungkyunkwan University（成均馆大学机械工程学院）；Department of Applied Artificial Intelligence, Sungkyunkwan University（成均馆大学应用人工智能系）；Department of Software, Sungkyunkwan University（成均馆大学软件系）
Georgia Institute of Technology（佐治亚理工学院）；University of North Carolina, Charlotte（北卡罗来纳大学夏洛特分校）
In this paper, we develop a framework for path-planning on abstractions that are not provided to the agent a priori but instead emerge as a function of the available computational resources. We show how a path-planning problem in an environment can be systematically approximated by solving a sequence of easier to solve problems on abstractions of the original space. The properties of the problem are analyzed, and a number of theoretical results are presented and discussed. A numerical example is presented to show the utility of the approach and to corroborate the theoretical findings. We concl…
National University of Singapore（新加坡国立大学）；Massachusetts Institute of Technology（麻省理工学院）
This paper presents a recursive reasoning formalism of Bayesian optimization (BO) to model the reasoning process in the interactions between boundedly rational, self-interested agents with unknown, complex, and costly-to-evaluate payoff functions in repeated games, which we call Recursive Reasoning-Based BO (R2-B2). Our R2-B2 algorithm is general in that it does not constrain the relationship among the payoff functions of different agents and can thus be applied to various types of games such as constant-sum, general-sum, and common-payoff games. We prove that by reasoning at level 2 or more a…
LAAS-CNRS（法国国家科学研究中心系统分析与架构实验室）；Universite de Toulouse（图卢兹大学）；Artificial and Natural Intelligence Toulouse Institute (ANITI)（图卢兹人工与自然智能研究所（ANITI））
We consider the human-aware task planning problem where a human-robot team is given a shared task with a known objective to achieve. Recent approaches tackle it by modeling it as a team of independent, rational agents, where the robot plans for both agents' (shared) tasks. However, the robot knows that humans cannot be administered like artificial agents, so it emulates and predicts the human's decisions, actions, and reactions. Based on earlier approaches, we describe a novel approach to solve such problems, which models and uses execution-time observability conventions. Abstractly, this mode…
Imperial College London（伦敦帝国学院）；University of Southampton（南安普顿大学）
Game theory's prescriptive power typically relies on full rationality and/or self-play interactions. In contrast, this work sets aside these fundamental premises and focuses instead on heterogeneous autonomous interactions between two or more agents. Specifically, we introduce a new and concise representation for repeated adversarial (constant-sum) games that highlight the necessary features that enable an automated planing agent to reason about how to score above the game's Nash equilibrium, when facing heterogeneous adversaries. To this end, we present TeamUP, a model-based RL algorithm desi…
University of California, Berkeley（加州大学伯克利分校）；KTH Royal Institute of Technology（KTH皇家理工学院）；Stanford University（斯坦福大学）
The actions of an autonomous vehicle on the road affect and are affected by those of other drivers, whether overtaking, negotiating a merge, or avoiding an accident. This mutual dependence, best captured by dynamic game theory, creates a strong coupling between the vehicle's planning and its predictions of other drivers' behavior, and constitutes an open problem with direct implications on the safety and viability of autonomous driving technology. Unfortunately, dynamic games are too computationally demanding to meet the real-time constraints of autonomous driving in its continuous state and a…
IMT Lille Douai（里尔-杜埃国立高等矿业电信学院）；Université de Lille（里尔大学）；University Rey Juan Carlos（胡安卡洛斯国王大学）；Valencian Research Institute for AI（瓦伦西亚人工智能研究院）；Universitat Politècnica de València（瓦伦西亚理工大学）
Open and shared manufacturing factories typically dispose of a limited number of robots that should be properly allocated to tasks in time and space for an effective and efficient system performance. In particular, we deal with the dynamic capacitated production planning problem with sequence independent setup costs where quantities of products to manufacture and location of robots need to be determined at consecutive periods within a given time horizon and products can be anticipated or backordered related to the demand period. We consider a decentralized multi-agent variant of this problem i…
