NeurIPS 2019: MineRL Challenge 1st place | Alexey Skrynnik (rus)

Uploaded By: Myvideo

Published on

15 Dec 2019

5 views

0

0 votes

0

About Share Download Add to

Video lecture from the RL Research Groups scientific seminar. Join us: Alexey Skrynnik's presentation about their CDS MIPT team first place solution of NeurIPS 2019: MineRL challenge. Details of the competition, 1st and 2nd round algorithms and methods. Recorded at the seminar on 05/12/2019. Slides: Challenge:

Share with your friends

Link:

Embed:

<iframe width="640" height="360" src="//myvideo.cc/embed/bVIvL29UZFBsWHIxL2c0UWJoR2JQTVQvQVdCZzFiUkFEdkZVRWdCZU5zaz0" 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

Сводки с полей @ NeurIPS 2019 Павел Калайдин

3 months ago

00:18:34

Сводки с полей @ NeurIPS 2019 Павел Калайдин

1 27%

Сводки с полей @ NeurIPS 2019 Дмитрий Бабаев

3 months ago

00:13:59

Сводки с полей @ NeurIPS 2019 Дмитрий Бабаев

1 83%

Сводки с полей @ NeurIPS 2019 Артем Соболев

3 months ago

00:19:55

Сводки с полей @ NeurIPS 2019 Артем Соболев

1 57%

Сводки с полей @ NeurIPS 2019 Данила Савенков

3 months ago

00:17:32

Сводки с полей @ NeurIPS 2019 Данила Савенков

1 14%

The moment we stopped understanding AI AlexNet

5 months ago

00:17:38

The moment we stopped understanding AI AlexNet

1 69%

Future Computers Will Be Radically Different (Analog Computing) | Veritasium

11 months ago

00:21:41

Future Computers Will Be Radically Different (Analog Computing) | Veritasium

244 90%

Чего БОИШЬСЯ то и СБУДЕТСЯ: разоблачение мифа

12 months ago

00:20:53

Чего БОИШЬСЯ то и СБУДЕТСЯ: разоблачение мифа

1 38%

Избыточный риск стабильных обучающих алгоритмов. Егор Клочков

4 years ago

00:58:44

Избыточный риск стабильных обучающих алгоритмов. Егор Клочков

5 45%

Razvan Pascanu - Continual learning for deep learning and deep reinforcement learning

4 years ago

00:54:06

Razvan Pascanu - Continual learning for deep learning and deep reinforcement learning

17 58%

Обзор статей по обучению с подкреплением с NeurIPS 2019, часть 2

5 years ago

00:36:13

Обзор статей по обучению с подкреплением с NeurIPS 2019, часть 2

1 23%

SLIDE: Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning with Beidi Chen...

5 years ago

00:30:04

SLIDE: Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning with Beidi Chen...

6 14%

Advancements in Machine Learning with Sergey Levine - #355

5 years ago

00:42:17

Advancements in Machine Learning with Sergey Levine - #355

8 65%

NeurIPS 2019 Outstanding New Directions Paper Award w/ slides

5 years ago

00:18:58

NeurIPS 2019 Outstanding New Directions Paper Award w/ slides

10 88%

Reinforcement Learning: Past, Present, and Future Perspectives | NeurIPS 2019 (w/ slides)

5 years ago

02:03:45

Reinforcement Learning: Past, Present, and Future Perspectives | NeurIPS 2019 (w/ slides)

19 67%

Efficient Computing for Deep Learning, Robotics, and AI (Vivienne Sze) | MIT Deep Learning Series

5 years ago

01:18:49

Efficient Computing for Deep Learning, Robotics, and AI (Vivienne Sze) | MIT Deep Learning Series

5 92%

Toward a General AI-Agent Architecture | Rich Sutton, DeepMind ALberta | NeurIPS 2019

5 years ago

00:34:43

Toward a General AI-Agent Architecture | Rich Sutton, DeepMind ALberta | NeurIPS 2019

8 59%

Panel Discussion: Bridging Game Theory and Deep Learning | NeurIPS 2019

5 years ago

00:43:07

Panel Discussion: Bridging Game Theory and Deep Learning | NeurIPS 2019

7 20%

Learning Meaningful Representations of Life - 2 | NeurIPS 2019

5 years ago

01:43:18

Learning Meaningful Representations of Life - 2 | NeurIPS 2019

4 68%

Learning in Dynamic Multi-Agent Environments | va Tardos | Game Theory | NeurIPS 2019

5 years ago

00:43:02

Learning in Dynamic Multi-Agent Environments | va Tardos | Game Theory | NeurIPS 2019

8 69%

Biological and Artificial Reinforcement Learning Panel Discussion | NeurIPS 2019

5 years ago

00:57:19

Biological and Artificial Reinforcement Learning Panel Discussion | NeurIPS 2019

6 40%

MEMENTO: Further Progress Through Forgetting | NeurIPS 2019 | Reinforcement Learning

5 years ago

00:13:57

MEMENTO: Further Progress Through Forgetting | NeurIPS 2019 | Reinforcement Learning

3 67%

Learning Meaningful Representations of Life - 1 | NeurIPS 2019

5 years ago

01:41:17

Learning Meaningful Representations of Life - 1 | NeurIPS 2019

8 6%

Обзор работ по генеративным моделям с NeurIPS 2019

5 years ago

00:48:08

Обзор работ по генеративным моделям с NeurIPS 2019

25 38%

Обзор статей по обучению с подкреплением с NeurIPS 2019, часть 1

5 years ago

01:05:39

Обзор статей по обучению с подкреплением с NeurIPS 2019, часть 1

2 88%

0 Comments

Guest