Incorporating Prior Knowledge into Temporal difference Networks.
Britton WolfeJames HarpePublished in: J. Comput. Sci. (2014)
Keyphrases
- temporal difference
- incorporating prior knowledge
- td learning
- function approximation
- evaluation function
- reinforcement learning
- prior knowledge
- monte carlo
- model free
- temporal difference learning
- reinforcement learning algorithms
- action selection
- temporal difference methods
- step size
- supervised learning
- policy evaluation
- pairwise
- convergence rate
- multi objective
- data mining