Search

We present an action model learning system known as ARMS (Action-Relation Modelling System) for automatically discovering action models from a set of successfully observed plans. Current artificial intelligence (Al) planners show impressive performance in many real world and artificial domains, but they all require the definition of an action model. ARMS is aimed at automatically learning action models from observed example plans, where each example plan is a sequence of action traces. These action models can then be used by the human editors to refine. The expectation is that this system will lessen the burden of the human editors in designing action models from scratch. In this paper, we describe the ARMS in detail. To learn action models, ARMS gathers knowledge on the statistical distribution of frequent sets of actions in the example plans. It then builds a weighted propositional satisfiability (weighted SAT) problem and solves it using a weighted MAXSAT solver. Furthermore, we show empirical evidence that ARMS can indeed learn a good approximation of the finally action models effectively. © 2007, Cambridge University Press.

AI planning requires the definition of action models using a formal action and plan description language, such as the standard Planning Domain Definition Language (PDDL), as input. However, building action models from scratch is a difficult and time-consuming task, even for experts. In this paper, we develop an algorithm called ARMS (action-relation modelling system) for automatically discovering action models from a set of successful observed plans. Unlike the previous work in action-model learning, we do not assume complete knowledge of states in the middle of observed plans. In fact, our approach works when no or partial intermediate states are given. These example plans are obtained by an observation agent who does not know the logical encoding of the actions and the full state information between the actions. In a real world application, the cost is prohibitively high in labelling the training examples by manually annotating every state in a plan example from snapshots of an environment. To learn action models, ARMS gathers knowledge on the statistical distribution of frequent sets of actions in the example plans. It then builds a weighted propositional satisfiability (weighted MAX-SAT) problem and solves it using a MAX-SAT solver. We lay the theoretical foundations of the learning problem and evaluate the effectiveness of ARMS empirically. (C) 2006 Elsevier B.V. All rights reserved.

We present an action model learning system known as ARMS (Action-Relation Modelling System) for automatically discovering action models from a set of successfully observed plans. Current artificial intelligence (Al) planners show impressive performance in many real world and artificial domains, but they all require the definition of an action model. ARMS is aimed at automatically learning action models from observed example plans, where each example plan is a sequence of action traces. These action models can then be used by the human editors to refine. The expectation is that this system will lessen the burden of the human editors in designing action models from scratch. In this paper, we describe the ARMS in detail. To learn action models, ARMS gathers knowledge on the statistical distribution of frequent sets of actions in the example plans. It then builds a weighted propositional satisfiability (weighted SAT) problem and solves it using a weighted MAXSAT solver. Furthermore, we show empirical evidence that ARMS can indeed learn a good approximation of the finally action models effectively. © 2007, Cambridge University Press.

AI planning requires the definition of action models using a formal action and plan description language, such as the standard Planning Domain Definition Language (PDDL), as input. However, building action models from scratch is a difficult and time-consuming task, even for experts. In this paper, we develop an algorithm called ARMS (action-relation modelling system) for automatically discovering action models from a set of successful observed plans. Unlike the previous work in action-model learning, we do not assume complete knowledge of states in the middle of observed plans. In fact, our approach works when no or partial intermediate states are given. These example plans are obtained by an observation agent who does not know the logical encoding of the actions and the full state information between the actions. In a real world application, the cost is prohibitively high in labelling the training examples by manually annotating every state in a plan example from snapshots of an environment. To learn action models, ARMS gathers knowledge on the statistical distribution of frequent sets of actions in the example plans. It then builds a weighted propositional satisfiability (weighted MAX-SAT) problem and solves it using a MAX-SAT solver. We lay the theoretical foundations of the learning problem and evaluate the effectiveness of ARMS empirically. (C) 2006 Elsevier B.V. All rights reserved.

We present an action model learning system known as ARMS (Action-Relation Modelling System) for automatically discovering action models from a set of successfully observed plans. Current artificial intelligence (Al) planners show impressive performance in many real world and artificial domains, but they all require the definition of an action model. ARMS is aimed at automatically learning action models from observed example plans, where each example plan is a sequence of action traces. These action models can then be used by the human editors to refine. The expectation is that this system will lessen the burden of the human editors in designing action models from scratch. In this paper, we describe the ARMS in detail. To learn action models, ARMS gathers knowledge on the statistical distribution of frequent sets of actions in the example plans. It then builds a weighted propositional satisfiability (weighted SAT) problem and solves it using a weighted MAXSAT solver. Furthermore, we show empirical evidence that ARMS can indeed learn a good approximation of the finally action models effectively. © 2007, Cambridge University Press.

AI planning requires the definition of action models using a formal action and plan description language, such as the standard Planning Domain Definition Language (PDDL), as input. However, building action models from scratch is a difficult and time-consuming task, even for experts. In this paper, we develop an algorithm called ARMS (action-relation modelling system) for automatically discovering action models from a set of successful observed plans. Unlike the previous work in action-model learning, we do not assume complete knowledge of states in the middle of observed plans. In fact, our approach works when no or partial intermediate states are given. These example plans are obtained by an observation agent who does not know the logical encoding of the actions and the full state information between the actions. In a real world application, the cost is prohibitively high in labelling the training examples by manually annotating every state in a plan example from snapshots of an environment. To learn action models, ARMS gathers knowledge on the statistical distribution of frequent sets of actions in the example plans. It then builds a weighted propositional satisfiability (weighted MAX-SAT) problem and solves it using a MAX-SAT solver. We lay the theoretical foundations of the learning problem and evaluate the effectiveness of ARMS empirically. (C) 2006 Elsevier B.V. All rights reserved.

Model-based techniques for reactive systems generally assume the availability of a state machine that describes the behavior of the system under study. However, the assumption may not always hold in reality. Even the assumption holds, the state machine could be invalidated when the system evolves. This triggers the study of adaptive model checking, which necessitates an iterative construction of a state machine for a system. In this paper, we propose a dynamic learning approach based on genetic algorithm to iteratively generate a finite-state automaton from a given system. In view of the fact that modern systems are apt to change, our algorithm postpones expensive equivalence checking until the associated accuracy is required for the verification of some properties. We explain in details the core learning process of our algorithm, including encoding the model and its synthesis from a given training set. Experimental results show that our algorithm is scalable in memory consumption. Dynamic model learning technique helps model checking of evolving reactive system. © 2006 IEEE.

Model-based techniques for reactive systems generally assume the availability of a state machine that describes the behavior of the system under study. However, the assumption may not always hold in reality. Even the assumption holds, the state machine could be invalidated when the system evolves. This triggers the study of adaptive model checking, which necessitates an iterative construction of a state machine for a system. In this paper, we propose a dynamic learning approach based on genetic algorithm to iteratively generate a finite-state automaton from a given system. In view of the fact that modern systems are apt to change, our algorithm postpones expensive equivalence checking until the associated accuracy is required for the verification of some properties. We explain in details the core learning process of our algorithm, including encoding the model and its synthesis from a given training set. Experimental results show that our algorithm is scalable in memory consumption. Dynamic model learning technique helps model checking of evolving reactive system. © 2006 IEEE.

Model-based techniques for reactive systems generally assume the availability of a state machine that describes the behavior of the system under study. However, the assumption may not always hold in reality. Even the assumption holds, the state machine could be invalidated when the system evolves. This triggers the study of adaptive model checking, which necessitates an iterative construction of a state machine for a system. In this paper, we propose a dynamic learning approach based on genetic algorithm to iteratively generate a finite-state automaton from a given system. In view of the fact that modern systems are apt to change, our algorithm postpones expensive equivalence checking until the associated accuracy is required for the verification of some properties. We explain in details the core learning process of our algorithm, including encoding the model and its synthesis from a given training set. Experimental results show that our algorithm is scalable in memory consumption. Dynamic model learning technique helps model checking of evolving reactive system. © 2006 IEEE.