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

Lecture

TD Learning: Temporal Difference Learning

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 introduces Temporal Difference Learning (TD learning) and the standard TD(0) algorithm for estimating values in reinforcement learning. It covers the concept of V-values, state-values, and the Bellman equation for value consistency of neighboring states. The lecture also explains how TD methods explore the graph over time, compare values at neighboring time steps, and update values based on 'temporal difference'.

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 (7)

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.

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.

Policy

Policy is a deliberate system of guidelines to guide decisions and achieve rational outcomes. A policy is a statement of intent and is implemented as a procedure or protocol. Policies are generally adopted by a governance body within an organization. Policies can assist in both subjective and objective decision making. Policies used in subjective decision-making usually assist senior management with decisions that must be based on the relative merits of a number of factors, and as a result, are often hard to test objectively, e.

Policy analysis

Policy analysis or public policy analysis is a technique used in the public administration sub-field of political science to enable civil servants, nonprofit organizations, and others to examine and evaluate the available options to implement the goals of laws and elected officials. People who regularly use policy analysis skills and techniques on the job, particularly those who use it as a major part of their job duties are generally known by the title Policy Analyst.

Related lectures (31)

Reinforcement Learning: Q-Learning

Covers Q-Learning in reinforcement learning, exploring action values, policies, and the societal impact of algorithms.

Reinforcement Learning: TD Learning and SARSA Variants

Discusses reinforcement learning, focusing on temporal difference learning and SARSA algorithm variations.

Mini-Batches in On- and Off-Policy Deep Reinforcement Learning

Explains the significance of mini-batches in Deep Reinforcement Learning and the differences between on-policy and off-policy methods.

Deep Reinforcement Learning: Mini-Batches and Policy Methods

Discusses deep reinforcement learning methods, focusing on mini-batches and the implications of on-policy and off-policy training techniques.

Reinforcement Learning: SARSA Algorithm