-
公开(公告)号：US20200074315A1
公开(公告)日：2020-03-05
申请号：US16121281
申请日：2018-09-04
摘要： Techniques regarding autonomous generation of one or more sets of diverse plans are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a planner component, operably coupled to the processor, that can generate a first plan based on a planning task. The computer executable components can also comprise a modification component, operably coupled to the processor, that can generate a modification to the planning task to facilitate generation of a second plan by the planner component. The second plan can be a variant of the first plan.
-
公开(公告)号：US20170364856A1
公开(公告)日：2017-12-21
申请号：US15182627
申请日：2016-06-15
CPC分类号： G06Q10/063112 , G06N5/003
摘要： A computer-implemented method, computerized apparatus and computer program product for decomposing multisite heterogeneous workforce scheduling problems. An instance of a multisite heterogeneous workforce scheduling problem comprising a set of work items and a set of technicians is obtained. A measure of likelihood that a pair of work items belong to the same sub-problem in a decomposition of the problem instance into a plurality of sub-problems, such that a union of solutions to the plurality of sub-problems is a solution to the problem, is calculated. The measure calculation comprises calculating one or more components indicating a relation between the pair of work items and technicians potentially scheduled to execute either of them. A solution to the problem is generated by solving the plurality of sub-problems in the decomposition obtained based on a partitioning of the set of work items induced by the measure and aggregating solutions to the plurality of sub-problems.
-
公开(公告)号：US20230342653A1
公开(公告)日：2023-10-26
申请号：US17660036
申请日：2022-04-21
摘要： Technology for: (i) receiving a domain-dependent artificial intelligence planning problem including definitions for a plurality of operators; (ii) creating an initial version of a label set, which defines an initial version of an action space, with the label set including a plurality of labels, and with each label of the plurality of labels respectively corresponding to the operators of the plurality of operators; (iii) performing, automatically and by machine logic, a label reduction on the initial version of the label set to obtain a reduced version of the label set that defines a reduced action space; and (iv) recasting the artificial planning problem as a first Markov decision process using the reduced version of label set.
-
公开(公告)号：US11755923B2
公开(公告)日：2023-09-12
申请号：US16205212
申请日：2018-11-29
IPC分类号： G06N5/02 , G06F11/34 , G06F21/56 , G06F11/30 , G06Q10/00 , G06N5/045 , G06N20/00 , G06N5/04 , G06N3/042 , G06N5/043
CPC分类号： G06N5/02 , G06F11/3024 , G06F11/3409 , G06F21/56 , G06N3/042 , G06N5/04 , G06N5/043 , G06N5/045 , G06N20/00 , G06Q10/00 , G06F2221/033
摘要： Performance of a computer running a plan recognition application is improved by obtaining, with a user interface implemented on the computer, a specification of a plan recognition problem, including a plurality of candidate observations; formulating at least one planning problem, with the computer, based on the specification; solving the at least one planning problem, with the computer, to determine at least one plan. The at least one plan is post-processed, with the computer, to determine at least one of the candidate observations which should be selected to solve the plan recognition problem; and the plan recognition problem is solved, with the computer, using the at least one of the candidate observations which should be selected to solve the plan recognition problem. Less CPU time is typically required for the solution as compared to techniques without guidance for selecting the observations.
-
公开(公告)号：US20230177368A1
公开(公告)日：2023-06-08
申请号：US17546022
申请日：2021-12-08
发明人： Junkyu Lee , Michael Katz , Shirin Sohrabi Araghi , Don Joven Ravoy Agravante , Miao Liu , Tamir Klinger , Murray Scott Campbell
CPC分类号： G06N7/005 , G06K9/6262
摘要： A computer-implemented method of integrating an Artificial Intelligence (AI) planner and a reinforcement learning (RL) agent through AI planning annotation in RL (PaRL) includes identifying an RL problem. A description received of a Markov decision process (MDP) having a plurality of states in an RL environment is used to generate an RL task to solve the RL problem. An AI planning model described in a planning language is received, and mapping state spaces from the MDP states in the RL environment to AI planning states of the AI planning model is performed. The RL task is generated with an AI planning task from the mapping to generate a PaRL task.
-
公开(公告)号：US10169291B2
公开(公告)日：2019-01-01
申请号：US15161303
申请日：2016-05-23
IPC分类号： G06F17/10
摘要： A computer program product comprising a non-transitory computer readable storage medium retaining program instructions configured to cause a processor to perform actions, which program instructions implement: a framework for creating a model of an NP-hard problem, the model comprising at least one entity selected from the group comprising: an objective, a variable, an equation and a constraint, wherein the framework provides methods for automatically transforming the model, comprising: one or more methods for manipulating or changing a status of the entity of the model, the methods comprising a method for imposing or ignoring the constraint; and one or more methods related to operations to be applied to the entity of the model.
-
公开(公告)号：US20170337042A1
公开(公告)日：2017-11-23
申请号：US15161303
申请日：2016-05-23
IPC分类号： G06F9/44
CPC分类号： G06F17/11
摘要： A computer program product comprising a non-transitory computer readable storage medium retaining program instructions configured to cause a processor to perform actions, which program instructions implement: a framework for creating a model of an NP-hard problem, the model comprising at least one entity selected from the group comprising: an objective, a variable, an equation and a constraint, wherein the framework provides methods for automatically transforming the model, comprising: one or more methods for manipulating or changing a status of the entity of the model, the methods comprising a method for imposing or ignoring the constraint; and one or more methods related to operations to be applied to the entity of the model.
-
公开(公告)号：US20230394325A1
公开(公告)日：2023-12-07
申请号：US17805572
申请日：2022-06-06
IPC分类号： G06N3/12
CPC分类号： G06N3/126
摘要： In an approach for improved artificial intelligence planning in an automated machine learning pipeline, a processor formulates an artificial intelligence planning problem. A processor receives a pre-defined stopping criterion for generating one or more plans for the artificial intelligence planning problem. A processor generates the one or more plans by executing a planning algorithm. A processor reformulates the artificial intelligence planning problem into a new artificial intelligence planning problem by forbidding plans that correspond to super-sets of the one or more plans. A processor generates one or more new plans based on the reformulation until the pre-defined stopping criterion is reached.
-
公开(公告)号：US20230206027A1
公开(公告)日：2023-06-29
申请号：US17646088
申请日：2021-12-27
CPC分类号： G06N3/0427 , G06N3/08 , H04L41/14
摘要： Some embodiments of the present invention are directed to a method of choosing the components for a satisficing planner using machine learning (ML) (for example, deep learning (DL)). Some embodiments of the present invention are directed to choosing search algorithm component(s) for a satisficing planner using ML (for example, DL). Some embodiments of the present invention are directed to choosing search refinement components (that is, search boosting component(s) and/or search pruning component(s)) for a satisficing planner using ML (for example, DL).
-
公开(公告)号：US11620486B2
公开(公告)日：2023-04-04
申请号：US15843194
申请日：2017-12-15
发明人： Michael Katz , Biplav Srivastava
摘要： Techniques facilitating estimating and visualizing entity to agent collaboration to facilitate automated plan generation are provided. In one example, a computer-implemented method comprises generating, by a device operatively coupled to a processor, a plan based on receiving first input data associated with an instance model. The computer-implemented method also comprises generating, by the device, a revised plan based on receiving second input data, associated with a revised instance model, from an entity. Furthermore, the computer-implemented method comprises, tracking, by the device, a contribution of the entity as a function of a modification from the instance model to the revised instance model.
-
-
-
-
-
-
-
-
-
搜索结果
23 条记录 (耗时 0.018 秒)
