alfa02
Re:The Bremen Drop Tower
on Saturday September 16, 2017 @11:40AM (#15265109)
Great to see this on hacker news. I can see the tower from my office.
Re:Evolution Strategies as a Scalable Alternative to Reinforcement Lea...
on Saturday March 25, 2017 @10:23AM (#13955766)
I am not sure at the moment. I guess the main problem of ES in a complex non-deterministic environment is that it would average over multiple local minima that occur in one generation which would result in a non-optimum solution. There are policy search methods that address this problem (e.g. VIPS https://scholar.google.com/citations?view_op=view_citation&h... , hierarchichal REPS https://scholar.google.com/citations?view_op=view_citation&h...).
Temporal credit assignment is another problem: the policy is updated after a full episode and there is no way to use the information which step was responsible for which reward. Policy search usually works well if the value function is very complex and the optimal policy is simple.
Re:Evolution Strategies as a Scalable Alternative to Reinforcement Lea...
on Saturday March 25, 2017 @05:39AM (#13954778)
Policy search is very effective. This is not a new finding as this article seems to suggest in the abstract.
Variants of ES have been used for years (http://dl.acm.org/citation.cfm?id=1645634). The article seems to ignore almost all the work in robotics, e.g. from Jan Peters' research group (http://www.jan-peters.net/ -> publications).
The good thing is that we have one more paper that justifies this research direction and a little bit more public attention.