Emergence of Locomotion Behaviours in Rich Environments — mentioned by sgillen

Sat, 17 Nov 2018 07:07:31 GMT

not a paper that came out this year but Emergence of Locomotion Behaviors in Rich Environments by Google deepmind: (https://arxiv.org/abs/1707.02286) made me realize that although RL is brittle and slow it can still be super effective the problem domains I care about (robot locomotion).

Paper and discussion history. A mention is not an endorsement.

Emergence of Locomotion Behaviours in Rich Environments — mentioned by BucketSort

Sat, 06 Jan 2018 02:53:47 GMT

You may have seen DeepMind's results last year where it trained 3D models to move through space in different ways, entitled "Emergence of Locomotion Behaviours in Rich Environments" ( https://arxiv.org/pdf/1707.02286.pdf , https://www.youtube.com/watch?v=hx_bgoTF7bs&feature=youtu.be). If you have a look in the paper, the method they use "Proximal Policy Optimization" is a great example of differentiable programming that does not include a neural network. I actually realized this last month when I was preparing a talk on deep learning, because I thought it used deep neural nets in its…

Paper and discussion history. A mention is not an endorsement.

Emergence of Locomotion Behaviours in Rich Environments · HackerPapers discussions

Emergence of Locomotion Behaviours in Rich Environments — mentioned by sgillen

Emergence of Locomotion Behaviours in Rich Environments — mentioned by BucketSort