Natasha Jaques

@natashamjaques - 33 本の動画

チャンネル登録者数 1.76万人

I'm an assistant professor at the University of Washington and a Staff Research Scientist at Google DeepMind. I give talks about my research on AI, machine l...

最近の動画

What Makes ChatGPT Chat? Modern AI for the layperson 39:04

What Makes ChatGPT Chat? Modern AI for the layperson

Reinforcement Learning (RL) for LLMs 33:10

Reinforcement Learning (RL) for LLMs

Social Reinforcement Learning talk at RLDM 37:41

Social Reinforcement Learning talk at RLDM

Badly trained policy after 40000 steps 1:40

Badly trained policy after 40000 steps

Multi-agent DQN training step 90000 trajectory video 1:40

Multi-agent DQN training step 90000 trajectory video

Multi-agent DQN training step 0 trajectory video 1:40

Multi-agent DQN training step 0 trajectory video

Learning to grab with bell as reward 1:14

Learning to grab with bell as reward

Intel Deep Learning Community of Practice talk 57:28

Intel Deep Learning Community of Practice talk

Natasha Jaques PhD Thesis Defense 1:30:15

Natasha Jaques PhD Thesis Defense

Personalized Multi-task Learning for Predicting Tomorrow's Mood, Stress, and Health 1:53

Personalized Multi-task Learning for Predicting Tomorrow's Mood, Stress, and Health

VHRED Cornell baseline 0:27

VHRED Cornell baseline

Influence agent in Harvest game 0:34

Influence agent in Harvest game

Influence agent in Cleanup game 0:34

Influence agent in Cleanup game

A3C baseline in Harvest 0:34

A3C baseline in Harvest

A3C baseline in Cleanup game 0:34

A3C baseline in Cleanup game

Agent trained with intrinsic social influence reward - Tragedy of the Commons 0:32

Agent trained with intrinsic social influence reward - Tragedy of the Commons

Agent trained with intrinsic social influence reward 0:13

Agent trained with intrinsic social influence reward

Influence reward in River with 1 influencer 0:34

Influence reward in River with 1 influencer

A3C will not free other agent trapped in a box 0:17

A3C will not free other agent trapped in a box

Influence agent frees compatriot trapped in a box 0:17

Influence agent frees compatriot trapped in a box

Note RNN 0:06

Note RNN

Q 0:08

Q

G 0:09

G

Basic LSTM 0:08

Basic LSTM

Psi 0:08

Psi

RL Tuner 0:08

RL Tuner

EDAExplorer PeakTutorial 0:31

EDAExplorer PeakTutorial

EDAExplorer ArtifactTutorial 0:29

EDAExplorer ArtifactTutorial

The Challenge 0:21

The Challenge

Affective Computing - Spring 2015 Virtual Visit 1:18

Affective Computing - Spring 2015 Virtual Visit

Eye gaze data 0:30

Eye gaze data

5 Lego Robots Dancing to Gangnam Style 0:34

5 Lego Robots Dancing to Gangnam Style

Lego Robot Gangnam Style 0:36

Lego Robot Gangnam Style

動画

ChatGPTチャットの特徴とは？一般人向けの最新AI 39:04

ChatGPTチャットの特徴とは？一般人向けの最新AI

13万 回視聴 - 2 週間前

LLM のための強化学習 (RL) 33:10

LLM のための強化学習 (RL)

4198 回視聴 - 2 か月前

Social Reinforcement Learning talk at RLDM 37:41

Social Reinforcement Learning talk at RLDM

1833 回視聴 - 9 か月前

Badly trained policy after 40000 steps 1:40

Badly trained policy after 40000 steps

1018 回視聴 - 1 年前

Multi-agent DQN training step 90000 trajectory video 1:40

Multi-agent DQN training step 90000 trajectory video

381 回視聴 - 1 年前

Multi-agent DQN training step 0 trajectory video 1:40

Multi-agent DQN training step 0 trajectory video

201 回視聴 - 1 年前

Learning to grab with bell as reward 1:14

Learning to grab with bell as reward

2183 回視聴 - 1 年前

Intel Deep Learning Community of Practice talk 57:28

Intel Deep Learning Community of Practice talk

5172 回視聴 - 3 年前

Natasha Jaques PhD Thesis Defense 1:30:15

Natasha Jaques PhD Thesis Defense

82万 回視聴 - 3 年前

Personalized Multi-task Learning for Predicting Tomorrow's Mood, Stress, and Health 1:53

Personalized Multi-task Learning for Predicting Tomorrow's Mood, Stress, and Health

1744 回視聴 - 3 年前

VHRED Cornell baseline 0:27

VHRED Cornell baseline

1044 回視聴 - 5 年前

Influence agent in Harvest game 0:34

Influence agent in Harvest game

959 回視聴 - 6 年前