Tolga Könik

Learning hierarchical task networks by observation

Knowledge-based planning methods offer benefits over classical techniques, but they are time consuming and costly to construct. There has been research on learning plan knowledge from search, but this can take substantial computer time and may even fail to find solutions on complex tasks. Here we describe another approach that observes sequences of operators taken from expert solutions to problems and learns hierarchical task networks from them. The method has similarities to previous algorithms for explanation-based learning, but differs in its ability to acquire hierarchical structures and in the generality of learned conditions. These increase the methods capability to transfer learned knowledge to other problems and supports the acquisition of recursive procedures. After presenting the learning algorithm, we report experiments that compare its abilities to other techniques on two planning domains. In closing, we review related work and directions for future research.

An Application of Transfer to American Football: From Observation of Raw Video to Control in a Simulated Environment

Automatic transfer of learned knowledge from one task or domain to another offers great potential to simplify and expedite the construction and deployment of intelligent systems. In practice however, there are many barriers to achieving this goal. In this article, we present a prototype system for the real-world context of transferring knowledge of American football from video observation to control in a game simulator. We trace an example play from the raw video through execution and adaptation in the simulator, highlighting the systems component algorithms along with issues of complexity, generality, and scale. We then conclude with a discussion of the implications of this work for other applications, along with several possible improvements.

A goal- and dependency-directed algorithm for learning hierarchical task networks

This paper describes a system for learning domain-dependent knowledge in the form of goal-indexed Hierarchical Task Networks (HTNs). DLIGHT is a goal-directed incremental learning algorithm which observes solution traces and generates rules for solving problems. One of the main challenges in learning this kind of knowledge is determining a good level of generality. Analytical methods, such as explanation-based macro-operator learning, construct very specific structures that guarantee a successful execution when applicable but generalize poorly to new problems. Previous goal-directed learning approaches produce hierarchical rules with more relaxed preconditions, but the learned knowledge suffers from over-generality. Our approach builds on one such approach but it strikes a better balance between generality and specificity. This is done by carrying out a goal-dependency analysis to determine the structure of the hierarchy and precondition of each rule to follow the successful solutions more closely while maintaining generality. We hypothesize that this algorithm produces HTNs that generalize well and can solve problems efficiently. We evaluate the systems behavior experimentally in several planning scenarios and conclude with related work and future research paths.

Inductive generalization of analytically learned goal hierarchies

We describe a new approach for learning procedural knowledge represented as teleoreactive logic programs using relational behavior traces as input. This representation organizes task decomposition skills hierarchically and associate explicitly defined goals with them. Our approach integrates analytical learning with inductive generalization in order to learn these skills. The analytical component predicts the goal dependencies in a successful solution and generates a teleoreactive logic program that can solve similar problems by determining the structure of the skill hierarchy and skill applicability conditions (preconditions), which may be overgeneral. The inductive component experiments with these skills on new problems and uses the data collected in this process to refine the preconditions. Our system achieves this by converting the data collected during the problem solving experiments into the positive and negative examples of preconditions that can be learned with a standard Inductive Logic Programming system. We show that this conversion uses one of the main commitments of teleoreactive logic programs: associating all skills with explicitly defined goals. We claim that our approach uses less expert effort compared to a purely inductive approach and performs better compared to a purely analytical approach.

A Statistical Approach to Incremental Induction of First-Order Hierarchical Knowledge Bases

Knowledge bases play an important role in many forms of artificial intelligence research. A simple approach to producing such knowledge is as a database of ground literals. However, this method is neither compact nor computationally tractable for learning or performance systems to use. In this paper, we present a statistical method for incremental learning of a hierarchically structured, first-order knowledge base. Our approach uses both rules and ground facts to construct succinct rules that generalize the ground literals. We demonstrate that our approach is computationally efficient and scales well to domains with many relations.

Duration Consistency Filtering for Qualitative Simulation

We present two new qualitative reasoning formalisms, and use them in the construction of a new type of filtering mechanism for qualitative simulators. Our new sign algebra, SR1*, facilitates reasoning about relationships among the signs of collections of real numbers. The comparison calculus, built on top of SR1*, is a general framework that can be used to qualitatively compare the behaviors of two dynamic systems or two excerpts of the behavior of a single dynamic system at different situations. These tools enable us to improve the predictive performance of qualitative simulation algorithms. We show that qualitative simulators can make better use of their input to deduce significant amounts of qualitative information about the relative lengths of the time intervals in their output behavior predictions. Simple techniques employing concepts like symmetry, periodicity, and comparison of the circumstances during multiple traversals of the same region can be used to build a list of facts representing the deduced information about relative durations. The duration consistency filter eliminates spurious behaviors leading to inconsistent combinations of these facts. Surviving behaviors are annotated with richer qualitative descriptions. Used in conjunction with other spurious behavior elimination methods, this approach would increase the ability of qualitative simulators to handle more complex systems.