The following pages link to (Q4737965):
Displaying 5 items.
- Hybrid least-squares algorithms for approximate policy evaluation (Q1959511) (← links)
- Reinforcement learning for a biped robot based on a CPG-actor-critic method (Q2383520) (← links)
- Restricted gradient-descent algorithm for value-function approximation in reinforcement learning (Q2389624) (← links)
- Dynamic portfolio choice: a simulation-and-regression approach (Q2402578) (← links)
- Bayesian Exploration for Approximate Dynamic Programming (Q4971589) (← links)
