Reusable Reinforcement Learning via Shallow Trails.
Yang YuShi-Yong ChenQing DaZhi-Hua ZhouPublished in: IEEE Trans. Neural Networks Learn. Syst. (2018)
Keyphrases
- reinforcement learning
- state space
- reinforcement learning algorithms
- function approximation
- temporal difference
- control problems
- markov decision processes
- question answering
- model free
- machine learning
- robotic control
- learning algorithm
- data sets
- software reuse
- optimal control
- direct policy search
- wall street journal
- natural language processing
- dynamic programming
- learning process
- transfer learning
- information extraction
- action selection
- evolutionary algorithm
- partially observable
- multi agent
- learning agents
- website
- genetic algorithm
- database