Strong 1-optimal stationary policies in denumerable Markov decision processes
From MaRDI portal
Publication:1108940
DOI10.1016/0167-6911(88)90113-2zbMath0654.90097OpenAlexW2038481005MaRDI QIDQ1108940
Rolando Cavazos-Cadena, Jean-Bernard Lasserre
Publication date: 1988
Published in: Systems \& Control Letters (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/0167-6911(88)90113-2
Markov decision processcompact action setscountable state spacesimultaneous Doeblin condition\(\alpha\)-discounted rewardbounded rewardsstationary average optimal policystrong 1-optimal policy
Related Items
Bias optimality and strong \(n\) \((n= -1,0)\) discount optimality for Markov decision processes ⋮ Remarks on sensitive equilibria in stochastic games with additive reward and transition structure ⋮ Blackwell optimal policies in a Markov decision process with a Borel state space ⋮ Strong 0-discount optimal policies in a Markov decision process with a Borel state space ⋮ Another Set of Conditions for Strongn(n = −1, 0) Discount Optimality in Markov Decision Processes ⋮ Sample-path optimality and variance-maximization for Markov decision processes ⋮ Are limits of \(\alpha\)-discounted optimal policies Blackwell optimal? A counterexample ⋮ Discount-sensitive equilibria in zero-sum stochastic differential games
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Necessary and sufficient conditions for a bounded solution to the optimality equation in average reward Markov decision chains
- Conditions for existence of average and Blackwell optimal stationary policies in denumerable Markov decision processes
- On optimality criteria for dynamic programs with long finite horizons
- Average, Sensitive and Blackwell Optimal Policies in Denumerable Markov Decision Chains with Unbounded Rewards
- Discrete Dynamic Programming
- On Finding Optimal Policies in Discrete Dynamic Programming with No Discounting
- Discrete Dynamic Programming with a Small Interest Rate
