Performance Dynamics and Termination Errors in Reinforcement Learning: A Unifying Perspective.
Nikki Lijing KuangClement H. C. LeungPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- viewpoint
- machine learning
- reinforcement learning algorithms
- error detection
- initial conditions
- error analysis
- database
- dynamical systems
- active rules
- optimal policy
- state space
- learning process
- objective function
- dynamic model
- robot control
- learning agents
- action selection
- learning classifier systems
- estimation error
- monte carlo
- cellular automata
- data mining