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

Lecture

Safe Learning for Autonomous Systems

Description

This lecture discusses challenges in control, safety, and coordination in uncertain dynamical systems, focusing on autonomous systems like autonomous cars. The instructor presents a model-based stochastic control approach, verification methods, and a paradigm shift towards learning and interaction. The lecture covers formulating safe learning problems, black-box information challenges, and a proposed safe learning approach. It also explores case studies in safe reinforcement learning and ongoing work in safe learning and control. The instructor delves into multi-agent systems formalized via game theory, Nash equilibria, learning in games, and learning Nash equilibria. The lecture concludes with discussions on bandit optimization, regret minimization, and model-based learning algorithms for Nash equilibria.

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.

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).

Nash equilibrium

In game theory, the Nash equilibrium, named after the mathematician John Nash, is the most common way to define the solution of a non-cooperative game involving two or more players. In a Nash equilibrium, each player is assumed to know the equilibrium strategies of the other players, and no one has anything to gain by changing only one's own strategy. The principle of Nash equilibrium dates back to the time of Cournot, who in 1838 applied it to competing firms choosing outputs.

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.

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.

Related lectures (27)

Policy Gradient and Actor-Critic Methods: Eligibility Traces Explained

Discusses policy gradient and actor-critic methods, focusing on eligibility traces and their application in reinforcement learning tasks.

Acquiring Data for Learning

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

Model-based versus Model-free Reinforcement Learning

Compares model-based and model-free reinforcement learning, highlighting the advantages of the former in adapting to reward changes and planning future actions.

Introduction to Game Theory Log in to Mediaspace to watch this video

Covers game theory fundamentals, Nash equilibrium, and strategic interactions in multi-agent systems.

Markov Games: Concepts and Applications in Reinforcement Learning Log in to Mediaspace to watch this video