1 / 13

Course Logistics

Course Logistics. CS533: Intelligent Agents and Decision Making M, W, F: 1:00—1:50 Instructor: Alan Fern (KEC2071) Office hours: by appointment (see me after class or send email) Course website (link on instructor’s home page) has Lecture notes and Assignments Grade based on projects:

kimo
Télécharger la présentation

Course Logistics

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Course Logistics • CS533: Intelligent Agents and Decision Making • M, W, F: 1:00—1:50 • Instructor: Alan Fern (KEC2071) • Office hours: by appointment (see me after class or send email) • Course website (link on instructor’s home page) has • Lecture notesand Assignments • Grade based on projects: • 65% Instructor Assigned Projects (mostly implementation and evaluation) • 15% Mid Term (mostly about technical/theoretical material) • 20% Student Selected Final Project • Assigned Projects (work alone) • Generally will be implementing and evaluating one or more algorithms • Final Project (teams allowed) • Last month of class • You select a project related to course content

  2. Some AI Planning Problems Solitaire Fire & RescueResponse Planning Real-Time Strategy Games Legged Robot Control Network Security/Control Helicopter Control

  3. Some AI Planning Problems • Health Care • Personalized treatment planning • Hospital Logistics/Scheduling • Transportation • Autonomous Vehicles • Supply Chain Logistics • Air traffic control • Assistive Technologies • Dialog Management • Automated assistants for elderly/disabled • Household robots • Personal planner

  4. Some AI Planning Problems • Sustainability • Smart grid • Forest fire management • Species Conservation Planning • Personalized Education/Training • Intelligent lesson planning • Intelligent agents for training simulators • Surveillance and Information Gathering • Intelligent sensor networks • Semi-Autonomous UAVs

  5. Common Elements • We have a controllable system that can change state over time (in some predictable way) • The state describes essential information about system(the visible card information in Solitaire) • We have an objective that specifies which states, or state sequences, are more/less preferred • Can (partially) control the system state transitions by taking actions • Problem: At each moment must select an action to optimize the overall objective • Produce most preferred state sequences

  6. Some Dimensions of AI Planning Actions Observations World sole sourceof change vs. other sources fully observable vs. partially observable ???? Goal deterministic vs. stochastic instantaneous vs. durative

  7. Classical Planning Assumptions(primary focus of AI planning until early 90’s) Actions Observations World sole sourceof change ???? fully observable deterministic instantaneous Goalachieve goal condition

  8. Classical Planning Assumptions(primary focus of AI planning until early 90’s) Actions Observations World sole sourceof change ???? fully observable deterministic instantaneous Goalachieve goal condition Greatly limits applicability

  9. Stochastic/Probabilistic Planning: Markov Decision Process (MDP) Model Actions Observations World sole sourceof change fully observable ???? stochastic instantaneous Goalmaximize expected reward over lifetime We will primarilyfocus on MDPs

  10. Stochastic/Probabilistic Planning: Markov Decision Process (MDP) Model Probabilistic state transition (depends on action) Action from finite set World State ???? Goalmaximize expected reward over lifetime

  11. Example MDP State describesall visible infoabout cards Action are the different legal card movements ???? Goalwin the game or play max # of cards

  12. Course Outline Course is structured around algorithms for solving MDPs • Different assumptions about knowledge of MDP model • Different assumptions about prior knowledge of solution • Different assumptions about how MDP is represented 1) Markov Decision Processes (MDPs) Basics • Basic definitions and solution techniques • Assume an exact MDP model is known • Exact solutions for small/moderate size MDPs 2) Monte-Carlo Planning • Assumes an MDP simulator is available • Approximate solutions for large MDPs

  13. Course Outline 3) Reinforcement learning • MDP model is not known to agent • Exact solutions for small/moderate MDPs • Approximate solutions for large MDPs 4) Planning w/ Symbolic Representations of Huge MDPs • Symbolic Dynamic Programming • Classical planning for deterministic problems • (as time allows)

More Related