The on-line shortest path problem under partial monitoring

MaRDI QIDQ3174159zbMATH OpenFDO

Authors András György, György Ottucsàk, Tamás Linder, Gábor Lugosi

Publication date 12 October 2011

Full work available at URL http://www.jmlr.org/papers/v8/gyoergy07a.html

zbMATH Keywords

multi-armed bandit problemon-line learningshortest path problem

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Games involving graphs (91A43)

Recommendations

• The Shortest Path Problem Under Partial Monitoring
• Online linear optimization and adaptive routing
• Adaptive routing with end-to-end feedback: distributed learning and geometric approaches
• Efficient algorithms for online decision problems.
• Efficient algorithms for online decision problems

Cited in

(16)

• Randomized prediction of individual sequences
• The covering Canadian traveller problem
• Online linear optimization and adaptive routing
• Bayesian Incentive-Compatible Bandit Exploration
• Adaptive routing with end-to-end feedback: distributed learning and geometric approaches
• Combinatorial bandits
• Online learning of Nash equilibria in congestion games
• The Shortest Path Problem Under Partial Monitoring
• Multi-armed bandit-based hyper-heuristics for combinatorial optimization problems
• Online learning of network bottlenecks via minimax paths
• Adversarial bandits with knapsacks
• Online learning for route planning with on-time arrival reliability
• A unified analysis of nonstochastic delayed feedback for combinatorial semi-bandits, linear bandits, and MDPs
• Online non-additive path learning under full and partial information
• Convergence to equilibrium of no-regret dynamics in congestion games
• Sensor networks: from dependence analysis via matroid bases to online synthesis

This page was built for publication: The on-line shortest path problem under partial monitoring

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3174159)