| Convexity and Convergence in Gradient Descent |
HackMD |
Sharath |
In this, we talk about strong and smooth convex functions and their convergence rates in case of gradient descent |
| Notes on Stability of Dynamical Systems |
HackMD |
Sharath |
In this notes, we discuss discrete and continuous dynamical systems and their stability properties |
| Policy Gradient Theorem |
HackMD |
Raj |
Derivation and explanation for the policy gradient theorem in Reinforcement Learning |
| Reproducing Kernel Hilbert Spaces |
HackMD |
Sharath |
These notes review some of the fundamental concepts of linear algebra like vector spaces, inner product spaces, etc., and then introduces the basic concepts of RKHS. |
| Guaranteed computation of robot trajectories |
HackMD |
Uddesh |
A contractor-based approach is proposed for guaranteed integration of state equations. The framework is based on the use of tubes as envelopes of feasible trajectories. |