An introduction to stochastic control theory, path integrals and reinforcement learning

zbMATH Open1338.93341MaRDI QIDQ2804092FDOQ2804092

Authors: Hilbert J. Kappen 

Publication date: 27 April 2016

Recommendations

• Path integrals and symmetry breaking for optimal control theory
• A generalized path integral control approach to reinforcement learning
• Machine Learning and Control Theory
• Optimal control as a graphical model inference problem
• Learning optimal control in deterministic systems

zbMATH Keywords

stochastic optimal controlreinforcement learningpath integral control

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic systems in control theory (general) (93E03)

Cited In (9)

• Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
• Optimal lock-down intensity: a stochastic pandemic control approach of path integral
• Multi-agent formation control based on Bell-shaped potential functions
• A bag-of-paths framework for network data analysis
• Path-integral-based reinforcement learning algorithm for goal-directed locomotion of snake-shaped robot
• Scoring a goal optimally in a soccer game under Liouville-like quantum gravity action
• Inferring Obstacles and Path Validity from Visibility-Constrained Demonstrations
• Whence the Expected Free Energy?
• Existence of the optimal control for stochastic boundary control problems governed by semilinear parabolic equations

This page was built for publication: An introduction to stochastic control theory, path integrals and reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2804092)