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

Lecture

Reinforcement Learning for Pacman

In course

ME-314: Concurrent engineering project

L'étudiant apprend à appliquer les compétences acquises en travaillant dans une équipe responsable d'une portion d'un projet plus vaste. ...

Description

This lecture covers the application of reinforcement learning to teach Pacman to play autonomously, focusing on policy gradient methods and Markov decision processes. It discusses the challenges faced, such as the large parameter space, and proposes solutions like log linear parametrization and vectorization.

Official source

Related concepts (25)

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.

Intelligent agent

In artificial intelligence, an intelligent agent (IA) is an agent acting in an intelligent manner; It perceives its environment, takes actions autonomously in order to achieve goals, and may improve its performance with learning or acquiring knowledge. An intelligent agent may be simple or complex: A thermostat or other control system is considered an example of an intelligent agent, as is a human being, as is any system that meets the definition, such as a firm, a state, or a biome.

Software agent

In computer science, a software agent or software AI is a computer program that acts for a user or other program in a relationship of agency, which derives from the Latin agere (to do): an agreement to act on one's behalf. Such "action on behalf of" implies the authority to decide which, if any, action is appropriate. Some agents are colloquially known as bots, from robot. They may be embodied, as when execution is paired with a robot body, or as software such as a chatbot executing on a phone (e.g.

Embodied agent

In artificial intelligence, an embodied agent, also sometimes referred to as an interface agent, is an intelligent agent that interacts with the environment through a physical body within that environment. Agents that are represented graphically with a body, for example a human or a cartoon animal, are also called embodied agents, although they have only virtual, not physical, embodiment. A branch of artificial intelligence focuses on empowering such agents to interact autonomously with human beings and the environment.

Multi-agent system

A multi-agent system (MAS or "self-organized system") is a computerized system composed of multiple interacting intelligent agents. Multi-agent systems can solve problems that are difficult or impossible for an individual agent or a monolithic system to solve. Intelligence may include methodic, functional, procedural approaches, algorithmic search or reinforcement learning. Despite considerable overlap, a multi-agent system is not always the same as an agent-based model (ABM).

Related lectures (31)

Acquiring Data for Learning

Explores training robots through reinforcement learning and learning from demonstration, highlighting challenges in human-robot interaction and data collection.

Safe Learning for Autonomous Systems

Explores challenges in control, safety, and coordination for autonomous systems like autonomous cars, focusing on safe learning and Nash equilibria.

Markov Decision Processes: Dynamic Programming Techniques

Discusses Markov Decision Processes and dynamic programming techniques for solving optimal policies in various scenarios.

Advanced Machine Learning: Discrete Reinforcement Learning

Introduces the basics of Reinforcement Learning, covering discrete states, actions, policies, value functions, MDPs, and optimal policies.

Safe Learning in Robotics: Quo Vadis?