[AIRG] OpenAI - Robot hand trained via reinforcement learning (10/17)

["Kuusisto, Finn" <FKuusisto@xxxxxxxxxxxxx>]

Hi all,

This week I'll be discussing some recent  reinforcement learning work coming out of OpenAI. Pretty interesting results training a physical robotic hand to manipulate objects via reinforcement learning entirely in simulation.
Blog:  https://blog.openai.com/learning-dexterity/
Paper:  https://arxiv.org/abs/1808.00177

Meet at:

CS 3310

4pm, 10/17

See you all there,

Finn

Finn Kuusisto, PhD
Postdoctoral Fellow
Regenerative Biology Laboratory
Morgridge Institute for Research
www.morgridge.org