Natasha Jaques
What Makes ChatGPT Chat? Modern AI for the layperson
39:04
Natasha Jaques
Reinforcement Learning (RL) for LLMs
33:10
Natasha Jaques
Social Reinforcement Learning talk at RLDM
37:41
Natasha Jaques
Badly trained policy after 40000 steps
1:40
Natasha Jaques
Multi-agent DQN training step 90000 trajectory video
1:40
Natasha Jaques
Multi-agent DQN training step 0 trajectory video
1:40
Natasha Jaques
Learning to grab with bell as reward
1:14
Natasha Jaques
Intel Deep Learning Community of Practice talk
57:28
Natasha Jaques
Natasha Jaques PhD Thesis Defense
1:30:15
Natasha Jaques
Personalized Multi-task Learning for Predicting Tomorrow's Mood, Stress, and Health
1:53
Natasha Jaques
VHRED Cornell baseline
0:27
Natasha Jaques
Influence agent in Harvest game
0:34
Natasha Jaques
Influence agent in Cleanup game
0:34
Natasha Jaques
A3C baseline in Harvest
0:34
Natasha Jaques
A3C baseline in Cleanup game
0:34
Natasha Jaques
Agent trained with intrinsic social influence reward - Tragedy of the Commons
0:32
Natasha Jaques
Agent trained with intrinsic social influence reward
0:13
Natasha Jaques
Influence reward in River with 1 influencer
0:34
Natasha Jaques
A3C will not free other agent trapped in a box
0:17
Natasha Jaques
Influence agent frees compatriot trapped in a box
0:17
Natasha Jaques
Note RNN
0:06
Natasha Jaques
Q
0:08
Natasha Jaques
G
0:09
Natasha Jaques
Basic LSTM
0:08
Natasha Jaques
Psi
0:08
Natasha Jaques
RL Tuner
0:08
Natasha Jaques
EDAExplorer PeakTutorial
0:31
Natasha Jaques
EDAExplorer ArtifactTutorial
0:29
Natasha Jaques
The Challenge
0:21
Natasha Jaques
Affective Computing - Spring 2015 Virtual Visit
1:18
Natasha Jaques
Eye gaze data
0:30
Natasha Jaques
5 Lego Robots Dancing to Gangnam Style
0:34
Natasha Jaques
Lego Robot Gangnam Style
0:36