A Critic for LISP
نویسنده
چکیده
Our goal is to establish the conceptual foundations for using the computational power that is or will be available on computer systems. Much of the available computing power is wasted, however, if users have difficulty understanding and llsing the full potential of these systems. Too much attention in the past has been given to the technology of computer systems and not enough to the effects of that technology, which has produced inadequate solutions to realworld problems, imposed unnecessary constraints on users, and failed to respond to changing needs. We have designed and implemented a critic for LISP as a prototype of an intelligent support system. Critics enhance incremental learning of a system and support learning strategies stich as learning on demand. Our LISP-critic has knowledge about how to improve LISP programs locally, following a style as defined by its rules. The advice given is based on the hypothesized knowledge of the user contained in the system's model of the user. Additional tools (e.g. a knowledge browser and visualization support) are available to explain and illustrate the advice. The LISP-CRITIC has been used by intermediate and expert LISP programmers and has proven to be a valuable tool for incremental learning of LISP and for improving programs.
منابع مشابه
User Modelling in Critics Based on a Study of Human Experts
Computer-based critics are an effective approach for using knowledge-based systems to support cooperative problem solving but need to be extended with user modelling capabilities. Efforts to do this in the USP.cRITIC system using statistical methods indicated the need to pursue additional techniques for implicit acquisition of knowledge about the user. A verbal protocol study of human experts a...
متن کاملOnActor-Critic Algorithms
In this article, we propose and analyze a class of actor-critic algorithms. These are two-time-scale algorithms in which the critic uses temporal difference learning with a linearly parameterized approximation architecture, and the actor is updated in an approximate gradient direction, based on information provided by the critic. We show that the features for the critic should ideally span a su...
متن کاملOn Adaptive Critic Architectures in Feedback Control
Two feedback control systems are designed that employ the adaptive critic architecture, which consists of two neural networks, one of which (the critic) tunes the other. The first application is a deadzone compensator, where it is shown that the adaptive critic structure is a natural consequence of the mathematical problem of inversion of an unknown function. In this situation the adaptive crit...
متن کاملBeyond Adaptive Critic - Creative Learning for Intelligent Autonomous Mobile Robots
Intelligent industrial and mobile robots may be considered proven technology in structured environments. Teach programming and supervised learning methods permit solutions to a variety of applications. However, we believe that to extend the operation of these machines to more unstructured environments requires a new learning method. Both unsupervised learning and reinforcement learning are pote...
متن کاملG Uide a Ctor - C Ritic for C Ontinuous C Ontrol
Actor-critic methods solve reinforcement learning problems by updating a parameterized policy known as an actor in a direction that increases an estimate of the expected return known as a critic. However, existing actor-critic methods only use values or gradients of the critic to update the policy parameter. In this paper, we propose a novel actor-critic method called the guide actor-critic (GA...
متن کامل