Hidden Strengths and Limitations: An Empirical Investigation of Reinforcement Learning.
Gerald DeJongPublished in: ICML (2000)
Keyphrases
- reinforcement learning
- function approximation
- robotic control
- action selection
- model free
- state space
- machine learning
- markov decision processes
- multi agent
- learning algorithm
- multiagent learning
- direct policy search
- dynamic programming
- learning process
- optimal policy
- learning classifier systems
- multiscale
- learning capabilities
- control problems
- temporal difference learning
- stochastic approximation
- neural network