Lectures related to N-step TD Methods: SARSA and Expected SARSA

Explicit Stabilised Methods: Applications to Bayesian Inverse Problems

Explores explicit stabilised Runge-Kutta methods and their application to Bayesian inverse problems, covering optimization, sampling, and numerical experiments.

First steps toward deep reinforcement learning

Explores the shift to deep reinforcement learning through neural networks for direct policy learning, bypassing Q-values and V-values.

Optimal Transport: Gradient Flows

Explores optimal transport, gradient flows, the implicit Euler scheme, and the heat equation in the context of Dirichlet energy functional.

Implicit or Explicit

Explores implicit and explicit methods in numerical analysis using Euler's paths.

Numerical Methods: ODE RK Schemes

Covers ODE RK schemes, including explicit RK stages and accuracy computation.

General Introduction into Artificial Neural Networks: part 3

Covers learning by rewards in deep reinforcement learning without math details.

Explicit RK Methods

Explains explicit Runge-Kutta methods up to order 4 and conditions for method's order.

Implicit Methods: Retrograde Euler

Covers the retrograde Euler method, an implicit numerical scheme used to solve equations and the concept of convergence order.