A Tour of Reinforcement Learning: The View from Continuous Control · HackerPapers discussions

A Tour of Reinforcement Learning: The View from Continuous Control — mentioned by jamessb

Sun, 10 Jan 2021 22:05:56 GMT

Ben Recht [0] has worked on control theory and reinforcement learning. See his blog post "What we've Learned to control" [1] and the survey paper "A Tour of Reinforcement Learning: The View from Continuous Control" [2] may be of interest. [0]: https://people.eecs.berkeley.edu/~brecht/ [1]: https://www.argmin.net/2020/06/29/tour-revisited/ [2]: https://arxiv.org/abs/1806.09460

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

A Tour of Reinforcement Learning: The View from Continuous Control — mentioned by currymj

Mon, 18 Feb 2019 21:34:35 GMT

If you have a good model, and can use model-based optimal control which has been understood for decades, then that is good but there's also not really a research problem? You can just do the simple, robust thing and it will work great. (i.e. "to publish more papers" is actually a legitimate reason if your job is explicitly to publish papers) You may enjoy the article, "A Tour of Reinforcement Learning: The View from Continuous Control". At least that researcher would agree that people doing RL don't pay enough attention to "classical" control. https://arxiv.org/abs/1806.09460

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

A Tour of Reinforcement Learning: The View from Continuous Control — mentioned by rocketflumes

Sun, 22 Jul 2018 15:47:24 GMT

for more on that subject - check out this recent RL and OCT survey by Ben Recht, also from UC Berkeley: https://arxiv.org/abs/1806.09460

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

A Tour of Reinforcement Learning: The View from Continuous Control — mentioned by johnmoberg

Sun, 22 Jul 2018 15:47:16 GMT

Ben's blog series culminated in a nice article[1] touring reinforcement learning. He also held a tutorial on the topic at ICML[2]. They might address some of your concerns. [1]: https://arxiv.org/abs/1806.09460 [2]: https://www.facebook.com/icml.imls/videos/428757614305426

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