Abstract Greedy algorithms for NLP such as transition-based parsing are prone to error propagation. One way overcome this problem is allow the algorithm backtrack and explore an alternative solution in cases where new evidence contradicts explored so far. In order implement a behavior, we use reinforcement learning let action gets better reward than continuing current solution. We test idea on ...

The popular use of backtracking as a control strategy for theorem proving in PROLOG and in Truth-MaintenanceSystems (TMS) led to increased interest in various schemes for enhancing the efficiency of backtrack search. Researchers have referred to these enhancement schemes by the names ‘ ‘Intelligent Backtracking’ ’ (in PROLOG), ‘ ‘Dependencydirected-backtracking” (in TMS) and others. Those impro...

It has been realized that the computational complexity of model-based diagnosis makes the mechanism impractical for real-world diagnosis tasks. One way to overcome this disadvantage is to focus the diagnosis on a reduced diagnostic space. we have proposed an improved critical diagnosis reasoning method 6] based on the method IMPLODE 5] proposed by Raiman, de Kleer and Saraswat. The improved met...

Pathological dependency cycles occur in state-space planners when control structures cannot efficiently determine a maximal matching for a bipartite operator/binding graph. Without proper search control, the planner will require many computationally expensive backtracks to arrive at a solution. We present a method for improving planning efficiency in the midst of pathological dependency cycles ...

Complete algorithms for solving propositional satis ability fall into twomain classes: backtracking (e.g., the Davis-Putnam Procedure [4]) and resolution (e.g., Directional Resolution [9]). Roughly speaking, backtracking amounts to \guessing" (making assumption), while resolution invokes \thinking" (inference). Experimental results show that both \pure guessing" and \pure thinking" might be ine...

We present a new method to represent variable bindings in the Warren Abstract Machine WAM so that ages of variable bindings can be easily found using this new representation The age of a variable bound to a ground term will be the youngest choice point such that backtracking to that choice point can make that variable an unbound variable again In other words the age of a variable bound to a gro...

The ability to perform both causal (means-end) and geometric reasoning is important in order to achieve autonomy for advanced robotic systems. In this paper, we describe work in progress on planning for a humanoid two-arm robotic system where task and path planning capabilities have been integrated into a coherent planning framework. We address a number of challenges of integrating combined tas...

In this paper, we develop a formalism called a distributed constraint satisfaction problem (distributed CSP) and algorithms for solving distributed CSPs. A distributed CSP is a constraint satisfaction problem in which variables and constraints are distributed among multiple agents. Various application problems in Distributed Artificial Intelligence can be formalized as distributed CSPs. We pres...

NaXi pictograph, which is the only hieroglyph in use is important for researching into the evolution of the character. The research on the recognition of printed NaXi pictograph characters is now just beginning. The major problem with machine printed NaXi pictograph character segmentation is the shape of the letter depending on its location in the word. In this paper, a machine printed NaXi pic...