activity
20132023
most citedQT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation

713 citations · 2.3k across the 20 of their papers we have counts for

collaborators
Showing 2019Show all

1 paper · 1 filter

cs.LG2019★ 15 cited

Watch, Try, Learn: Meta-Learning from Demonstrations and Reward

Allan Zhou, Eric Jang, Daniel Kappler +7

Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations.…