Min max generalization for deterministic batch mode reinforcement learning: relaxation schemes

DOI10.1137/120867263MaRDI QIDQ2873838zbMATH OpenOpenAlexFDO

Authors R. Fonteneau, D. Ernst, B. Boigelot, Quentin Louveaux

Publication date 27 January 2014

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.711.5580

zbMATH Keywords

batch mode reinforcement learningcomputational complexitymin--max problemnonconvex optimizationrelaxation schemes

Mathematics Subject Classification ID

Existence of solutions for minimax problems (49J35) Methods involving semicontinuity and convergence; relaxation (49J45) Learning and adaptive systems in artificial intelligence (68T05) Nonconvex programming, global optimization (90C26) Minimax problems in mathematical programming (90C47) Abstract computational complexity for mathematical programming problems (90C60)

Recommendations

• Towards min max generalization in reinforcement learning
• A unified DC programming framework and efficient DCA based approaches for large scale batch reinforcement learning
• Learning Near-Optimal Policies with Bellman-Residual Minimization Based Fitted Policy Iteration and a Single Sample Path
• Efficient reinforcement learning in deterministic systems with value function generalization
• Batch mode reinforcement learning based on the synthesis of artificial trajectories

Cited in

(2)

• Towards min max generalization in reinforcement learning
• Batch mode reinforcement learning based on the synthesis of artificial trajectories

Describes a project that uses

Uses Software

• SeDuMi

This page was built for publication: Min max generalization for deterministic batch mode reinforcement learning: relaxation schemes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2873838)