Andere Kunden interessierten sich auch für
![Co-evolutionary and Reinforcement Learning Techniques in Computer Go]( "Co-evolutionary and Reinforcement Learning Techniques in Computer Go")
Co-evolutionary and Reinforcement Learning Techniques in Computer Go53,99 €![Poker Learner: Reinforcement Learning Applied to Texas Hold'em Poker]( "Poker Learner: Reinforcement Learning Applied to Texas Hold'em Poker")
Poker Learner: Reinforcement Learning Applied to Texas Hold'em Poker36,99 €![Lateral Control of Autonomous Vehicle Based on Reinforcement Learning]( "Lateral Control of Autonomous Vehicle Based on Reinforcement Learning")
Lateral Control of Autonomous Vehicle Based on Reinforcement Learning36,99 €![Stochastic Systems Divergence through Reinforcement Learning]( "Stochastic Systems Divergence through Reinforcement Learning")
Stochastic Systems Divergence through Reinforcement Learning44,99 €![Data Analysis Technologies: Computer Vision, Deep Learning, Big Data]( "Data Analysis Technologies: Computer Vision, Deep Learning, Big Data")
Data Analysis Technologies: Computer Vision, Deep Learning, Big Data51,99 €![e-Learning, Challenges and Impact on Education]( "e-Learning, Challenges and Impact on Education")
e-Learning, Challenges and Impact on Education32,99 €![Improved Reinforcement-Based Profile Learning for Documents Filtering]( "Improved Reinforcement-Based Profile Learning for Documents Filtering")
Improved Reinforcement-Based Profile Learning for Documents Filtering32,99 €
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.