1/18

Markov Decision Processes (MDPs) Part 1/2 (CS 188)

Pieter Abbeel UC Berkeley

Professor

1:25:00·2018·undergraduate level

This lecture introduces the formal definition of Markov Decision Processes (MDPs), exploring optimal policies, value iteration, and concepts of utilities and discounting in sequential decision-making.

AI & ML Reinforcement Learning Algorithms & Data Structures Markov Decision Processes Optimal Policies

COMPSCI 188, LEC 001 - Fall 2018

COMPSCI 188, LEC 001 - Pieter Abbeel, Daniel Klein

Copyright @2018 UC Regents; all rights reserved

Previous · Lecture 7

COMPSCI 188 - 2018-09-13 - Search with Other Agents: Expectimax, Utilities

Next · Lecture 9

Markov Decision Processes (MDPs) Part 2/2 (CS 188)

Comments

Add a comment...Sign in

Part of course22 lectures

CS 188: Introduction to Artificial Intelligence

Prof. Pieter Abbeel

Uninformed and A* heuristic search, constraint satisfaction, adversarial minimax/expectimax games, Markov decision processes, reinforcement learning, Bayes nets, and particle filtering.

View full syllabus →

Related lectures

Markov Decision Processes (MDPs) Part 2/2 (CS 188)

Pieter Abbeel · UC Berkeley

Next in CS 188 · Lecture 9

Lecture 14: Deep Reinforcement Learning (CS231n)

Fei-Fei Li, Justin Johnson & Serena Yeung · Stanford University

Shared subfield · Reinforcement Learning & Algorithms & Data Structures

Lecture 5, Part 1 (CS 285)

Sergey Levine · UC Berkeley

Shared subfield · Algorithms & Data Structures & Reinforcement Learning

Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning

Parham Panahi · Alberta Machine Intelligence Institute (Amii)

Shared subfield · Reinforcement Learning & Algorithms & Data Structures

UCL / DeepMind RL Lecture 5: Model-Free Control — ε-Greedy SARSA & Off-Policy Q-Learning

David Silver · Google DeepMind

Shared subfield · Reinforcement Learning & Algorithms & Data Structures

POPRi: Private Federated Learning using Preference-Optimized Synthetic Data

Charlie Hou · Google Research & TechTalks

Shared subfield · Algorithms & Data Structures & Reinforcement Learning