Atnaujintas knygų su minimaliais defektais pasiūlymas! Naršykite ČIA >>
Reinforcement learning (RL) consists of methods that automatically adjust behaviour based on numerical rewards and penalties. While use of the attribute-value framework is widespread in RL, it has limited expressive power. Logic languages, such as first-order logic, provide a more expressive framework, and their use in RL has led to the field of relational RL. This thesis develops a system for relational RL based on learning classifier systems (LCS). In brief, the system generates, evolves, and evaluates a population of condition-action rules, which take the form of definite clauses over first-order logic. Adopting the LCS approach allows the resulting system to integrate several desirable qualities: model-free and "tabula rasa" learning; a Markov Decision Process problem model; and importantly, support for variables as a principal mechanism for generalisation. The utility of variables is demonstrated by the system's ability to learn genuinely scalable behaviour - behaviour learnt in small environments that translates to arbitrary large versions of the environment without the need for retraining.
| Autorius: | Drew Mellor |
| Leidėjas: | LAP LAMBERT Academic Publishing |
| Išleidimo metai: | 2010 |
| Knygos puslapių skaičius: | 292 |
| ISBN-10: | 383830196X |
| ISBN-13: | 9783838301969 |
| Formatas: | 220 x 150 x 18 mm. Knyga minkštu viršeliu |
| Kalba: | Anglų |
Parašykite atsiliepimą apie „Reinforcement Learning, Logic and Evolutionary Computation: A Learning Classifier System Approach to Relational Reinforcement Learning“
