Reinforcement learning algorithms for solving classification problems.
Marco A. WieringHado van HasseltAuke-Dirk PietersmaLambert SchomakerPublished in: ADPRL (2011)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- model free
- markov decision processes
- eligibility traces
- reinforcement learning problems
- partially observable environments
- reinforcement learning methods
- temporal difference
- policy search
- learning algorithm
- reward function
- function approximation
- policy gradient
- solving problems
- convergence rate
- markov decision problems
- least squares
- active learning