If given manually-crafted goal selection knowledge, goal reasoning agents can dynamically determine which goals they should achieve in complex environments. These agents should instead learn goal selection knowledge through expert interaction. We describe T-ARTUE, a goal reasoning agent that performs case-based active and interactive learning to discover goal selection knowledge. We also report tests of its performance in a complex environment. We found that, under some conditions, T-ARTUE can quickly learn goal selection knowledge.

POMDP algorithms have made significant progress in recent years by allowing practitioners to find good solutions to increasingly large problems. Most approaches (including point-based and policy iteration techniques) operate by refining a lower bound of the optimal value function. Several approaches (e.g., HSVI2, SARSOP, grid-based approaches and online forward search) also refine an upper bound. However, approximating the optimal value function by an upper bound is computationally expensive and therefore tightness is often sacrificed to improve efficiency (e.g., sawtooth approximation). In this paper, we describe a new approach to efficiently compute tighter bounds by i) conducting a prioritized breadth first search over the reachable beliefs, ii) propagating upper bound improvements with an augmented POMDP and iii) using exact linear programming (instead of the sawtooth approximation) for upper bound interpolation. As a result, we can represent the bounds more compactly and significantly reduce the gap between upper and lower bounds on several benchmark problems.

This paper discusses a novel hybrid approach for text categorization that combines a machine learning algorithm, which provides a base model trained with a labeled corpus, with a rule-based expert system, which is used to improve the results provided by the previous classifier, by filtering false positives and dealing with false negatives. The main advantage is that the system can be easily fine-tuned by adding specific rules for those noisy or conflicting categories that have not been successfully trained. We also describe an implementation based on k-Nearest Neighbor and a simple rule language to express lists of positive, negative and relevant (multiword) terms appearing in the input text. The system is evaluated in several scenarios, including the popular Reuters-21578 news corpus for comparison to other approaches, and categorization using IPTC metadata, EUROVOC thesaurus and others. Results show that this approach achieves a precision that is comparable to top ranked methods, with the added value that it does not require a demanding human expert workload to train.

Multi-modal transportation is a logistics problem in which a set of goods have to be transported to different places, with the combination of at least two modes of transport, without a change of container for the goods. The goal of this paper is to describe TIMIPLAN, a system that solves multi-modal transportation problems in the context of a project for a big company. In this paper, we combine Linear Programming (LP) with automated planning techniques in order to obtain good quality solutions. The direct use of classical LP techniques is difficult in this domain, because of the non-linearity of the optimization function and constraints; and planning algorithms cannot deal with the entire problem due to the large number of resources involved. We propose a new hybrid algorithm, combining LP and planning to tackle the multi-modal transportation problem, exploiting the benefits of both kinds of techniques. The system also integrates an execution component that monitors the execution, keeping track of failures and replans if necessary, maintaining most of the plan in execution. We also present some experimental results that show the performance of the system.

A collection of landmarks is complete if the cost of a minimum-cost hitting set equals h + and there is a minimum-cost hitting set that is an optimal relaxed plan. We present an algorithm for generating a complete collection of landmarks and we show that this algorithm can be extended into effective polytime heuristics for optimal and satisficing planning. The new admissible heuristics are compared with current state-of-the-art heuristics for optimal planning on benchmark problems from the IPC.

In this paper, we show how to make a cognitive tutoring agent capable of precise causal reasoning by integrating constraints with data mining algorithms. Putting constraints on recorded interactions between the agent and learners during learning activities allows data mining algorithms to extract the causes of the learners’ problems. Subsequently, the agent uses this information to provide useful and customized explanations to learners.

We address the problem of simulate democratic elections via a set of competing agents.We propose a logical model based on a set of non-cooperative agents which compete for attracting a maximum number of votes from a population. Each agent builds a set of strategies (formed by the promises, actions and proposals of the agent) used to convince to the potential voters.

The main goal of this study is to identify bridging reading strategy — a strategy that a reader uses to make a connection from the current sentence to previous sentences to help understanding the meaning of the text. For a specific target sentence, there are two types of bridging: local and distal. Benchmarks were created to help represent each type of bridging. The two immediate prior sentences of each target sentence together created a benchmark for the local bridging. The benchmarks for distal bridging were those prior sentences, excluding two immediate prior sentences. There were three ways that distal benchmarks were created: chunks based-on paragraph, chunks based-on target sentence, and entire collection of prior sentences. The results showed that using modified benchmark by removing up to 4 words within a threshold 0.4 has significantly improved the identification of distal bridging reading strategy by 14% from the original benchmark evaluation. On the other hand, to identify local bridging, using modified benchmark by removing 4 words has significantly improved the identification by 19% from the original benchmark evaluation.

We propose and evaluate five related algorithms that automatically derive limited-size noun vocabularies from text documents of 2,000-30,000 words.The proposed algorithms combine Personalized Page Rank and principles of information maximization, and are applied to the WordNet graph for nouns. For the best-performing algorithm the difference between automatically generated reduced noun lexicons and those created by human writers is approximately 1-2 WordNet edges per lexical item. Our results also indicate the importance of performing word-sense disambiguation with sentence-level context information at the earliest stage of analysis.

Multi-robot task allocation is an important problem for heterogeneous mobile robots. Simultaneous allocations with which multiple tasks are being allocated concurrently tend to lead to more efficient allocations than online or single task allocations. However, the simultaneous allocation also increases the complexity in the winner determination process, especially when robots are required to collaborate in order to accomplish certain tasks. This paper presents a winner determination algorithm for the simultaneous allocation of multi-robot tasks. The complete approach layers alow-level coalition formation algorithm for solving one multi-robot task with a high-level simultaneous task allocation approach. We implement a tree-based winner determination algorithm with an iterative deepening A* (IDA*) search and show that the algorithm is able to generate the optimal task-coalition mapping in the initial round and the IDA* performs efficiently based on time and space complexities.