{"product_id":"reinforcement-learning-logic-and-evolutionary-computation-a-learning-classifier-system-approach-to-relational-reinforcement-learning-383830196x","title":"Reinforcement Learning, Logic and Evolutionary Computation: A Learning Classifier System Approach to Relational Reinforcement Learning","description":"\u003cp\u003e\u003cstrong\u003eISBN:\u003c\/strong\u003e 383830196X\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eAuthor:\u003c\/strong\u003e Mellor, Drew\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eCondition:\u003c\/strong\u003e New\u003c\/p\u003e\u003cp\u003eReinforcement 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.\u003c\/p\u003e","brand":"Mia Karts","offers":[{"title":"Default Title","offer_id":68223078990112,"sku":"NEW383830196X","price":150.0,"currency_code":"CAD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0980\/7426\/3840\/files\/51ysxCRmsIS.jpg?v=1794316179","url":"https:\/\/miakarts.com\/en-ca\/products\/reinforcement-learning-logic-and-evolutionary-computation-a-learning-classifier-system-approach-to-relational-reinforcement-learning-383830196x","provider":"Miakarts Books","version":"1.0","type":"link"}