Relevant Knowledge First - Reinforcement Learning and Forgetting in Knowledge Based Configuration
Ingo KreuzDieter RollerPublished in: CoRR (2001)
Keyphrases
- relevant knowledge
- reinforcement learning
- function approximation
- knowledge base
- temporal abstractions
- expert systems
- markov decision processes
- policy search
- transition model
- reinforcement learning algorithms
- optimal control
- control problems
- optimal policy
- dynamic programming
- learning algorithm
- learning problems
- learning capabilities
- robotic control
- state space
- incremental learning
- data sets
- transfer learning
- multi agent reinforcement learning
- learning process
- multi agent
- data mining