Q-learning for Markov decision processes with a satisfiability criterion
From MaRDI portal
Publication:1749413
DOI10.1016/j.sysconle.2018.01.003zbMath1386.93271OpenAlexW2794044232MaRDI QIDQ1749413
Suhail M. Shah, Vivek S. Borkar
Publication date: 16 May 2018
Published in: Systems \& Control Letters (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/j.sysconle.2018.01.003
Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40) Stochastic systems in control theory (general) (93E03)
Related Items
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- The Borkar-Meyn theorem for asynchronous stochastic approximations
- An analog of the minimax theorem for vector payoffs
- Dynamical systems and variational inequalities
- Stochastic approximation with two time scales
- Approachability in Stackelberg stochastic games with vector costs
- Approachable sets of vector payoffs in stochastic games
- The projection dynamic and the geometry of population games
- Learning Algorithms for Markov Decision Processes with Average Cost
- Estimation and control in discounted stochastic dynamic programming
- Survey of Measurable Selection Theorems
- Asynchronous Stochastic Approximations
- Evolutionary Games and Population Dynamics
- The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
- Structural Properties of Optimal Transmission Policies Over a Randomly Varying Channel
- Asynchronous stochastic approximation with differential inclusions
- Multiplicative updates outperform generic no-regret learning in congestion games
- Guaranteed performance regions in Markovian systems with competing decision makers
- Stochastic Approximations and Differential Inclusions
- Stochastic Approximations and Differential Inclusions, Part II: Applications
