Approachability in Stackelberg stochastic games with vector costs

DOI10.1007/s13235-016-0198-yzbMath1391.91029arXiv1411.0728OpenAlexW2471478425MaRDI QIDQ1707454

Dileep Kalathil, Vivek S. Borkar, Rahul Jain

Publication date: 3 April 2018

Published in: Dynamic Games and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1411.0728

Mathematics Subject Classification ID

Stochastic approximation (62L20) Stochastic games, stochastic differential games (91A15) Markov and semi-Markov decision processes (90C40)

Related Items

Learning in games with cumulative prospect theoretic preferences, Q-learning for Markov decision processes with a satisfiability criterion

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An analog of the minimax theorem for vector payoffs
• Approachability, regret and calibration: implications and equivalences
• Approachable sets of vector payoffs in stochastic games
• An actor-critic algorithm for constrained Markov decision processes
• Learning Algorithms for Markov Decision Processes with Average Cost
• Online Markov Decision Processes
• Markov Decision Processes with Arbitrary Reward Processes
• Survey of Measurable Selection Theorems
• The Lorenz attractor exists
• Asynchronous Stochastic Approximations
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• On Boundedness of Q-Learning Iterates for Stochastic Shortest Path Problems
• Guaranteed performance regions in Markovian systems with competing decision makers
• Stochastic Approximations and Differential Inclusions
• Stochastic Approximations and Differential Inclusions, Part II: Applications
• The Empirical Bayes Envelope and Regret Minimization in Competitive Markov Decision Processes
• Optimal control and viscosity solutions of Hamilton-Jacobi-Bellman equations