Lecture

Reinforcement Learning: Basics and Applications

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Description

This lecture introduces the fundamentals of reinforcement learning, focusing on learning through trial-and-error. It covers topics such as action values, Q-learning, deep reinforcement learning, and the application of RL in various scenarios like playing games and planning efficiently. The lecture also discusses the role of dopamine in signaling reward prediction errors and the distinction between goal-directed and habitual behavior in RL. Additionally, it explores the use of Monte Carlo estimation and model-based RL systems. The session concludes with insights on the challenges and benefits of scientific advancements in the context of societal wisdom.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Official source

Related concepts (32)

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.

Regional planning

Regional planning deals with the efficient placement of land-use activities, infrastructure, and settlement growth across a larger area of land than an individual city or town. Regional planning is related to urban planning as it relates land use practices on a broader scale. It also includes formulating laws that will guide the efficient planning and management of such said regions. Regional planning can be comprehensive by covering various subjects, but it more often specifies a particular subject, which requires region-wide consideration.

Urban planning

Urban planning, also known as town planning, city planning, regional planning, or rural planning, is a technical and political process that is focused on the development and design of land use and the built environment, including air, water, and the infrastructure passing into and out of urban areas, such as transportation, communications, and distribution networks and their accessibility.

Deep reinforcement learning

Deep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs (e.g.

Land-use planning

Land use planning is the process of regulating the use of land by a central authority. Usually, this is done to promote more desirable social and environmental outcomes as well as a more efficient use of resources. More specifically, the goals of modern land use planning often include environmental conservation, restraint of urban sprawl, minimization of transport costs, prevention of land use conflicts, and a reduction in exposure to pollutants.

Related lectures (64)

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.

Deep Learning Agents: Reinforcement Learning

Explores Deep Learning Agents in Reinforcement Learning, emphasizing neural network approximations and challenges in training multiagent systems.

Deep and Robust Reinforcement Learning Techniques

Discusses advanced reinforcement learning techniques, focusing on deep and robust methods, including actor-critic frameworks and adversarial learning strategies.

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