Off-policy temporal difference learning with distribution adaptation in fast mixing chains.
Arash GivchiMaziar PalhangPublished in: Soft Comput. (2018)
Keyphrases
- temporal difference learning
- function approximation
- fixed point
- evaluation function
- approximate value iteration
- reinforcement learning
- temporal difference
- game playing
- probability distribution
- markov decision process
- least squares
- support vector
- neural network
- linear programming
- random walk
- reinforcement learning algorithms
- policy iteration
- function approximators