Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

N-step TD Methods: SARSA and Expected SARSA

In course

CS-456: Deep reinforcement learning

This course provides an overview and introduces modern methods for reinforcement learning (RL.) The course starts with the fundamentals of RL, such as Q-learning, and delves into commonly used approaches, like PPO and DQN. The course will introduce student ...

Description

This lecture discusses the scaling problem of Temporal Difference (TD) algorithms and introduces n-step TD methods as a solution. It covers the concept of n-step SARSA and n-step expected SARSA, explaining how they improve the flow of information in reinforcement learning. The lecture also explores the use of n-step TD methods for estimating both action values and state values, providing a comprehensive overview of their implementation and benefits.

Instructors (2)

Caglar Gulcehre

Wulfram Gerstner

Wulfram Gerstner is Director of the Laboratory of Computational Neuroscience LCN at the EPFL. His research in computational neuroscience concentrates on models of spiking neurons and spike-timing dependent plasticity, on the problem of neuronal coding in single neurons and populations, as well as on the link between biologically plausible learning rules and behavioral manifestations of learning. He teaches courses for Physicists, Computer Scientists, Mathematicians, and Life Scientists at the EPFL. After studies of Physics in Tübingen and at the Ludwig-Maximilians-University Munich (Master 1989), Wulfram Gerstner spent a year as a visiting researcher in Berkeley. He received his PhD in theoretical physics from the Technical University Munich in 1993 with a thesis on associative memory and dynamics in networks of spiking neurons. After short postdoctoral stays at Brandeis University and the Technical University of Munich, he joined the EPFL in 1996 as assistant professor. Promoted to Associate Professor with tenure in February 2001, he is since August 2006 a full professor with double appointment in the School of Computer and Communication Sciences and the School of Life Sciences. Wulfram Gerstner has been invited speaker at numerous international conferences and workshops. He has served on the editorial board of the Journal of Neuroscience, Network: Computation in Neural Systems', Journal of Computational Neuroscience', and `Science'.

Official source

Related concepts (9)

Q-learning

Q-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. It does not require a model of the environment (hence "model-free"), and it can handle problems with stochastic transitions and rewards without requiring adaptations. For any finite Markov decision process (FMDP), Q-learning finds an optimal policy in the sense of maximizing the expected value of the total reward over any and all successive steps, starting from the current state.

Reinforcement learning

Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. Reinforcement learning differs from supervised learning in not needing labelled input/output pairs to be presented, and in not needing sub-optimal actions to be explicitly corrected.

Temporal difference learning

Temporal difference (TD) learning refers to a class of model-free reinforcement learning methods which learn by bootstrapping from the current estimate of the value function. These methods sample from the environment, like Monte Carlo methods, and perform updates based on current estimates, like dynamic programming methods. While Monte Carlo methods only adjust their estimates once the final outcome is known, TD methods adjust predictions to match later, more accurate, predictions about the future before the final outcome is known.

Runge–Kutta methods

In numerical analysis, the Runge–Kutta methods (ˈrʊŋəˈkʊtɑː ) are a family of implicit and explicit iterative methods, which include the Euler method, used in temporal discretization for the approximate solutions of simultaneous nonlinear equations. These methods were developed around 1900 by the German mathematicians Carl Runge and Wilhelm Kutta. The most widely known member of the Runge–Kutta family is generally referred to as "RK4", the "classic Runge–Kutta method" or simply as "the Runge–Kutta method".

Finite difference method

In numerical analysis, finite-difference methods (FDM) are a class of numerical techniques for solving differential equations by approximating derivatives with finite differences. Both the spatial domain and time interval (if applicable) are discretized, or broken into a finite number of steps, and the value of the solution at these discrete points is approximated by solving algebraic equations containing finite differences and values from nearby points.

Related lectures (28)

High Order Methods: Space Discretisation

Covers high order methods for space discretisation in linear differential systems.

Reinforcement Learning: Policy Gradient and Actor-Critic Methods

Provides an overview of reinforcement learning, focusing on policy gradient and actor-critic methods for deep artificial neural networks.

Explicit Stabilised Methods: Stochastic Differential Equations

Covers explicit stabilized methods for stiff stochastic differential equations, analyzing their properties and applications.

Neural Networks: Multilayer Learning

Covers the fundamentals of multilayer neural networks and deep learning, including back-propagation and network architectures like LeNet, AlexNet, and VGG-16.

Runge-Kutta Methods