- Title
- Reinforcement learning, logic and evolutionary computation: a learning classifier system approach to relational reinforcement learning
- Creator
- Mellor, Drew
- Relation
- https://www.lap-publishing.com/catalog/details/store/gb/book/978-3-8383-0196-9/reinforcement-learning,-logic-and-evolutionary-computation
- Publisher
- Lambert Academic Publishing
- Resource Type
- book
- Date
- 2009
- Description
- 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.
- Subject
- machine learning; logic programming; reinforcement learning; Markov Decision Process
- Identifier
- http://hdl.handle.net/1959.13/917640
- Identifier
- uon:8371
- Identifier
- ISBN:9783838301969
- Language
- eng
- Hits: 649
- Visitors: 616
- Downloads: 0