Natasha Jaques
20,500 Subscribers
What Makes ChatGPT Chat? Modern AI for the layperson
Natasha Jaques
Reinforcement Learning (RL) for LLMs
Natasha Jaques
Social Reinforcement Learning talk at RLDM
Natasha Jaques
Badly trained policy after 40000 steps
Natasha Jaques
Multi-agent DQN training step 0 trajectory video
Natasha Jaques
Multi-agent DQN training step 90000 trajectory video
Natasha Jaques
Learning to grab with bell as reward
Natasha Jaques
Intel Deep Learning Community of Practice talk
Natasha Jaques
Natasha Jaques PhD Thesis Defense
Natasha Jaques
Personalized Multi-task Learning for Predicting Tomorrow'
Natasha Jaques
VHRED Cornell baseline
Natasha Jaques
Influence agent in Harvest game
Natasha Jaques
A3C baseline in Harvest
Natasha Jaques
Influence agent in Cleanup game
Natasha Jaques
A3C baseline in Cleanup game
Natasha Jaques
Agent trained with intrinsic social influence reward - Trage
Natasha Jaques
Agent trained with intrinsic social influence reward
Natasha Jaques
Influence reward in River with 1 influencer
Natasha Jaques
A3C will not free other agent trapped in a box
Natasha Jaques
Influence agent frees compatriot trapped in a box
Natasha Jaques
Note RNN
Natasha Jaques
Q
Natasha Jaques
Basic LSTM
Natasha Jaques
RL Tuner
Natasha Jaques
G
Natasha Jaques
Psi
Natasha Jaques
EDAExplorer PeakTutorial
Natasha Jaques
EDAExplorer ArtifactTutorial
Natasha Jaques
The Challenge
Natasha Jaques
Affective Computing - Spring 2015 Virtual Visit
Natasha Jaques
Eye gaze data
Natasha Jaques
5 Lego Robots Dancing to Gangnam Style
Natasha Jaques
Lego Robot Gangnam Style
Natasha Jaques
Natasha Jaques
