Performance Dynamics and Termination Errors in Reinforcement Learning - A Unifying Perspective.
Nikki Lijing KuangClement H. C. LeungPublished in: AIKE (2018)
Keyphrases
- reinforcement learning
- function approximation
- dynamical systems
- viewpoint
- machine learning
- reinforcement learning algorithms
- state space
- dynamic model
- optimal control
- robotic control
- error accumulation
- collective behavior
- temporal difference
- error analysis
- real time
- data mining
- data sets
- model free
- action selection
- markov decision processes
- initial conditions
- genetic algorithm
- stochastic approximation
- multi agent reinforcement learning