History-dependent Evaluations in Partially Observable Markov Decision Process
From MaRDI portal
Publication:4990323
DOI10.1137/20M1332876zbMath1469.90154MaRDI QIDQ4990323
Publication date: 28 May 2021
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
Dynamic programming (90C39) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Markov and semi-Markov decision processes (90C40) Dynamical systems and their relations with probability theory and stochastic processes (37A50)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Repeated games with public uncertain duration process
- Uniform value in dynamic programming
- A convex analytic approach to Markov decision processes
- Incomplete information in Markovian decision models
- Blackwell optimality in Markov decision processes with partial observation.
- Optimal control of Markov processes with incomplete state information
- Strong Uniform Value in Gambling Houses and Partially Observable Markov Decision Processes
- Reduction of a Controlled Markov Model with Incomplete Data to a Problem with Complete Information in the Case of Borel State and Control Space
- Average Cost Dynamic Programming Equations For Controlled Markov Chains With Partial Observations
- Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
- Discrete Dynamic Programming
- On Near Optimality of the Set of Finite-State Controllers for Average Cost POMDP
- Discrete-Time Markovian Decision Processes with Incomplete State Observation
- Long-Term Values in Markov Decision Processes and Repeated Games, and a New Distance for Probability Spaces
This page was built for publication: History-dependent Evaluations in Partially Observable Markov Decision Process
