Skip to main content

Ctrl+K

Practical Reinforcement Learning: From Algorithms to Applications

Why This Book?

Modeling

Why Build a Model? For Whom?
Dynamics Models for Decision Making
Programs as Models

Numerical Trajectory Optimization

Discrete-Time Trajectory Optimization
Trajectory Optimization in Continuous Time

From Trajectories to Policies

Model Predictive Control
Dynamic Programming

Learning from Data

Approximate Dynamic Programming
Policy Parametrization Methods

Appendix

Example COCPs
Solving Initial Value Problems
Nonlinear Programming

References

Bibliography

Repository
Open issue

Search

Ctrl+K

By Pierre-Luc Bacon

© Copyright 2023.