On the Difficulty of Modular Reinforcement Learning for Real-World Partial Programming.
Sooraj BhatCharles Lee Isbell Jr.Michael MateasPublished in: AAAI (2006)
Keyphrases
- reinforcement learning
- real world
- wide range
- learning algorithm
- programming language
- data mining
- neural network
- function approximation
- synthetic data
- multi agent
- case study
- computer programming
- reinforcement learning algorithms
- data sets
- markov decision processes
- learning classifier systems
- development environment
- object oriented programming
- temporal difference learning
- programming environments
- modular neural networks
- dynamic programming
- multi agent systems
- search algorithm
- website
- genetic algorithm