Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks.
Chris DrummondPublished in: J. Artif. Intell. Res. (2002)
Keyphrases
- reinforcement learning
- state space
- user defined
- automatically generated
- multi agent
- optimal policy
- machine learning
- solution space
- benchmark problems
- markov decision processes
- probabilistic model
- solution quality
- function approximation
- reinforcement learning algorithms
- markov decision process
- stochastic approximation
- robotic control
- data sets
- control system
- optimal solution
- high level
- case study
- website
- decision making
- information retrieval
- data mining
- real world
- neural network