The following pages link to (Q3496174):
Displaying 4 items.
- On the properties of \(\epsilon\) (\(\geq 0)\) optimal policies in discounted unbounded return model (Q581259) (← links)
- Existence of optimal stationary policies in discounted Markov decision processes: Approaches by occupation measures (Q1327188) (← links)
- Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces (Q3119642) (← links)
- PAC Bounds for Discounted MDPs (Q3164829) (← links)