Shared July 31, 2018
In this video we discuss the paper: „DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills" by Xue Bin Peng, Pieter Abbeel, Sergey Levine and Michiel van de Panne.
Can robots learn to walk, strike, throw and jump from human examples? We answer this here.
Jump straight to the Review: https://youtu.be/2_CO82KObQY?t=52s
Note: We are reviewing this paper, and we were not part of the research or the team which authored this paper.
This is an initiative of Roboy.
Sign up for the NIPS - AI for prosthetics challenge:
Link for the paper:
Comparing humans with the best Reinforcement Learning algorithms
For the Love of Physics - Walter Lewin - May 16, 2011
Sergey Levine: Control as Inference and Soft Deep RL
What if you could trade a paperclip for a house? | Kyle MacDonald | TEDxVienna
DebConf 14: QA with Linus Torvalds
REST API concepts and examples
The most important lesson from 83,000 brain scans | Daniel Amen | TEDxOrangeCoast
World's Most Famous Hacker Kevin Mitnick & KnowBe4's Stu Sjouwerman Opening Keynote
3DeepLearner SIGGRAPH Series - Part 03 - DeepMimic
Ben Berman - Machine Learning and Level Generation
DICKS: Do you need to be one to be a successful leader?
This virtual stuntman could improve video game physics
SIGGRAPH Asia 2018: Skills from Videos paper (main video)
Deep Reinforcement Learning Toward Robotics
Deep Robotic Learning
Life is hard when you are simulated.