15:28
Self Play for Safety - Online Multi-Agent Adversarial Training for Provably Robust LLMs
39:04
What Makes ChatGPT Chat? Modern AI for the layperson
33:10
Reinforcement Learning (RL) for LLMs
37:41
Social Reinforcement Learning talk at RLDM
01:40
Badly trained policy after 40000 steps
01:40
Multi-agent DQN training step 90000 trajectory video
01:40
Multi-agent DQN training step 0 trajectory video
01:14
Learning to grab with bell as reward
57:28
Intel Deep Learning Community of Practice talk
01:30:15
Natasha Jaques PhD Thesis Defense
01:53
Personalized Multi-task Learning for Predicting Tomorrow's Mood, Stress, and Health
00:27
VHRED Cornell baseline
00:34
Influence agent in Harvest game
00:34
A3C baseline in Harvest
00:32
Agent trained with intrinsic social influence reward - Tragedy of the Commons
00:13
Agent trained with intrinsic social influence reward
00:17
A3C will not free other agent trapped in a box
00:17
Influence agent frees compatriot trapped in a box
00:06
Note RNN
00:08
Q
00:09
G
00:08
Basic LSTM
00:08
Psi
00:08
RL Tuner
00:31
EDAExplorer PeakTutorial
00:29
EDAExplorer ArtifactTutorial
00:21
The Challenge
01:18
Affective Computing - Spring 2015 Virtual Visit
00:30
Eye gaze data
00:34
5 Lego Robots Dancing to Gangnam Style
X
About
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 learning, and reinforcement learning. If you want to learn more, check out my website natashajaques.ai/.
Tags