Least-Squares Policy Iteration: Bias-Variance Trade-off in Control Problems.
Christophe ThieryBruno ScherrerPublished in: ICML (2010)
Keyphrases
- bias variance
- control problems
- trade off
- reinforcement learning methods
- markov games
- reinforcement learning
- continuous state spaces
- optimal control
- bias variance decomposition
- model free
- reinforcement learning algorithms
- temporal difference
- policy iteration
- adaptive control
- queueing systems
- low variance
- stochastic control
- bias variance analysis
- control method
- state space
- learning algorithm