DRL Course 2023 | Model-Free Reinforcement Learning: Monte-Carlo, SARSA, Q-Learning

Uploaded By: Myvideo

Published on

16 Sep 2024

2 views

0

0 votes

0

About Share Download Add to

Курс Deep Reinforcement Learning 2023: Сезон курсов: В четвертой лекции: - Рассматривается случай MDP с неизвестными функциями награды и перехода между состояниями - Рассмотрели подход Monte-Carlo и Temporal-Difference для нахождения Q-функции в этом случае - Обсудили epsilon-жадные политики - Вывили алгоритмы Monte-Carlo, SARSA и Q-learning Автор курса: Антон Плаксин, исследователь в группе и доцент Уральского федерального университета. Наши соц.сети: Telegram: Вконтакте: Канал с вакансиями в telegram: Канал с апдейтами по курсам: Как попасть в чат сообщества ODS Mattermost:

Share with your friends

Link:

Embed:

<iframe width="640" height="360" src="//myvideo.cc/embed/MURGMkdNTUR6K1lobHRwKzdSRnBCaGdYdmc4bVNGOWNJa0JMbkVqWlg1WT0" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>

Video Size:

Custom size:

x

Autoplay video

Hide player controls

Hide resume playing

Add to Playlist:

Favorites

My Playlist

Watch Later

DRL Course | Introduction to Reinforcement Learning. Cross-Entropy Method

2 months ago

01:30:49

DRL Course | Introduction to Reinforcement Learning. Cross-Entropy Method

11 47%

DRL Course | Практическое занятие 1. Cross-Entropy Method

2 months ago

01:21:36

DRL Course | Практическое занятие 1. Cross-Entropy Method

3 32%

DRL Course | Практическое занятие 2. PyTorch and Deep Cross-Entropy Method.

2 months ago

01:19:14

DRL Course | Практическое занятие 2. PyTorch and Deep Cross-Entropy Method.

11 63%

DRL Course | Value Function Approximation. Deep Q-Networks (DQN)

2 months ago

01:18:31

DRL Course | Value Function Approximation. Deep Q-Networks (DQN)

10 22%

DRL Course | Практическое занятие 4. Monte-Carlo and SARSA

2 months ago

00:53:37

DRL Course | Практическое занятие 4. Monte-Carlo and SARSA

1 8%

DRL Course | Introduction to Neural Networks. Deep Cross-Entropy Method

2 months ago

01:01:08

DRL Course | Introduction to Neural Networks. Deep Cross-Entropy Method

5 56%

DRL Course | Dynamic Programming. Policy and Value Iterations

2 months ago

00:57:45

DRL Course | Dynamic Programming. Policy and Value Iterations

3 83%

DRL Course | Model-Free Reinforcement Learning: Monte-Carlo, SARSA, Q-Learning

2 months ago

01:13:56

DRL Course | Model-Free Reinforcement Learning: Monte-Carlo, SARSA, Q-Learning

2 94%

DRL Course | Практическое занятие 3. Policy Iteration

2 months ago

01:17:06

DRL Course | Практическое занятие 3. Policy Iteration

3 70%

DRL Course | Практическое занятие 5. Deep Q-Networks (DQN)

2 months ago

00:54:42

DRL Course | Практическое занятие 5. Deep Q-Networks (DQN)

7 24%

DRL Course | Практическое занятие 6. Deep Deterministic Policy Gradient (DDPG)

2 months ago

01:15:12

DRL Course | Практическое занятие 6. Deep Deterministic Policy Gradient (DDPG)

8 20%

DRL Course | Policy Gradient

2 months ago

01:07:56

DRL Course | Policy Gradient

1 16%

DRL Course | Разбор домашних заданий 1-3

2 months ago

01:10:06

DRL Course | Разбор домашних заданий 1-3

7 9%

DRL Course | Разбор домашних заданий 4-6. Подведение итогов курса

2 months ago

00:48:12

DRL Course | Разбор домашних заданий 4-6. Подведение итогов курса

9 79%

DRL Course 2023 | Introduction to Reinforcement Learning. Cross-Entropy Method

2 months ago

01:35:04

DRL Course 2023 | Introduction to Reinforcement Learning. Cross-Entropy Method

20 84%

DRL Course 2023 | Introduction to Neural Networks. Deep Cross-Entropy Method

2 months ago

01:21:50

DRL Course 2023 | Introduction to Neural Networks. Deep Cross-Entropy Method

10 34%

DRL Course 2023 | Практическое занятие 1. Cross-Entropy Method.

2 months ago

01:26:35

DRL Course 2023 | Практическое занятие 1. Cross-Entropy Method.

10 86%

DRL Course 2023 | Практическое занятие 3. Policy Iteration

2 months ago

01:14:40

DRL Course 2023 | Практическое занятие 3. Policy Iteration

2 34%

DRL Course 2023 |Dynamic Programming. Policy and Value Iterations

2 months ago

01:14:28

DRL Course 2023 |Dynamic Programming. Policy and Value Iterations

4 31%

DRL Course 2023 | Model-Free Reinforcement Learning: Monte-Carlo, SARSA, Q-Learning

2 months ago

01:27:47

DRL Course 2023 | Model-Free Reinforcement Learning: Monte-Carlo, SARSA, Q-Learning

2 76%

DRL Course 2023 | Практическое занятие 2. PyTorch and Deep Cross-Entropy Method.

2 months ago

01:34:50

DRL Course 2023 | Практическое занятие 2. PyTorch and Deep Cross-Entropy Method.

18 44%

DRL Course 2023 | Практика 8. Multi-Armed Bandit

2 months ago

00:46:48

DRL Course 2023 | Практика 8. Multi-Armed Bandit

1 85%

DRL Course 2023 | Monte-Carlo and SARSA

2 months ago

01:27:47

DRL Course 2023 | Monte-Carlo and SARSA

1 62%

DRL Course 2023 | Value Function Approximation. Deep Q-Networks (DQN)

2 months ago

01:19:44

DRL Course 2023 | Value Function Approximation. Deep Q-Networks (DQN)

15 39%

0 Comments

Guest