Self-Improving Reactive Agents Based On Reinforcement Learning, Planning and Teaching.
Long Ji LinPublished in: Mach. Learn. (1992)
Keyphrases
- reactive agents
- reinforcement learning
- learning process
- function approximation
- multi agent
- learning algorithm
- state space
- reinforcement learning algorithms
- high school
- machine learning
- online learning
- model free
- markov decision processes
- learning environment
- temporal difference
- optimal policy
- teacher education
- computer programming
- e learning
- higher education
- distance education
- action selection
- computer technology
- learning experience
- web based learning
- programming course
- partially observable
- complex domains
- attitudes toward
- markov decision process
- reinforcement learning methods
- dynamic programming