We present a new approach to reinforcement learning in which the policies considered by the learning process are constrained by hierarchies of partially specified machines. This allows for the use of prior knowledge to reduce the search space and provides a framework in which knowledge can be transferred across problems and in which component solutions can be recombined to solve larger and more complicated problems. Our approach can be seen as providing a link between reinforcement learning and “behavior-based ” or “teleo-reactive ” approaches to control. We present provably convergent algorithms for problem-solving and learning with hierarchical machines and demonstrate their effectiveness on a problem with several thousand states. 1

We present an expressive agent design language for reinforcement learning that allows the user to constrain the policies considered by the learning process.The language includes standard features such as parameterized subroutines, temporary interrupts, aborts, and memory variables, but also allows for unspecified choices in the agent program. For learning that which isn’t specified, we present provably convergent learning algorithms. We demonstrate by example that agent programs written in the language are concise as well as modular. This facilitates state abstraction and the transferability of learned skills. 1

An important area of learning in autonomous agents is the ability to learn domain-specific models of actions to be used by planning systems. In this paper, we present methods by which an agent learns action models from its own experience and from its observation of a domain expert. These methods differ from previous work in the area in two ways: the use of an action model formalism which is better suited to the needs of a reactive agent, and successful implementation of noise-handling mechanisms. Training instances are generated from experience and observation, and a variant of GOLEM is used to learn action models from these instances. The integrated learning system has been experimentally validated in simulated construction and office domains. 1 INTRODUCTION Autonomous agents acting in complex environments must be capable of learning from experience, both to avoid the need for exhaustive preprogramming and to adapt to unanticipated or changing situations. Most such work has focused o...

This paper describes the use of task primitives in robot learning from observation. A framework has been developed that uses observed data to initially learn a task and then the agent goes on to increase its performance through repeated task performance (learning from practice). Data that is collected while a human performs a task is parsed into small parts of the task called primitives. Modules are created for each primitive that encode the movements required during the performance of the primitive, and when and where the primitives are performed. The feasibility of this method is currently being tested with agents that learn to play a virtual and an actual air hockey game. 1

In this paper, we examine the motivations for research on cognitive architectures and review some candidates that have been explored in the literature. After this, we consider the capabilities that a cognitive architecture should support, some properties that it should exhibit related to representation, organization, performance, and learning, and some criteria for evaluating such architectures at the systems level. In closing, we discuss some open issues that should drive future research in this important area. Key words: cognitive architectures, intelligent systems, cognitive processes 1

this document. 9.5.2 A comparison of CUE and libido

In its early stages, the field of artificial intelligence (AI) had as its main goal the invention of computer programs having the general problem solving abilities of humans. Along the way, there developed a major shift of emphasis from general-purpose programs toward "performance programs"---ones whose competence was highly specialized and limited to particular areas of expertise. In this paper I claim that AI is now at the beginning of another transition---one that will re-invigorate efforts to build programs of general, human-like competence. These programs will use specialized performance programs as tools, much like humans do. Keywords: autonomous agents, general problem solving, habile systems Copyright c fl1995 Nils J. Nilsson [This paper is being submitted to the AI Magazine.] 1 Diversions from the Main Goal Over forty years ago, soon after the birth of electronic computers, people began to think that human levels of intelligence might someday be realized in computer program...

This paper describes recent experiments in automatically contructing reactive agents. The method used is behavioural cloning, where the logged data from skilled, human operators are input to an induction program which outputs a control strategy for a complex control task. Initial studies were able to successfully construct such behavioural clones, but suffered from several drawbacks, namely, that the clones were brittle and difficult to understand. Current research is aimed at solving these problems by learning in a framework where there is a separation between an agent's goals and its knowledge of how to achieve them.

Abstract not found

symbolic machine learning