Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Schwab, Devin"'
Autor:
Schwab, Devin, Springenberg, Tobias, Martins, Murilo F., Lampe, Thomas, Neunert, Michael, Abdolmaleki, Abbas, Hertweck, Tim, Hafner, Roland, Nori, Francesco, Riedmiller, Martin
We present a method for fast training of vision based control policies on real robots. The key idea behind our method is to perform multi-task Reinforcement Learning with auxiliary tasks that differ not only in the reward to be optimized but also in
Externí odkaz:
http://arxiv.org/abs/1902.04706
Autor:
Schwab, Devin
For large Sequential Decision Making tasks, an agent may need to make lots of exploratory interactions within the environment in order to learn the optimal policy. Large amounts of exploration can be costly in terms of computation, time for interacti
Externí odkaz:
http://rave.ohiolink.edu/etdc/view?acc_num=case1441374844
Autor:
Schwab, Devin
A long standing goal of robotics research is to create algorithms that can automatically learn complex control strategies from scratch. Part of the challenge ofapplying such algorithms to robots is the choice of representation. Reinforcement Learning
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::16623e8642934cb11636438f1053382a
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
2012 IEEE 17th International Workshop on Computer Aided Modeling & Design of Communication Links & Networks (CAMAD); 1/ 1/2012, p271-275, 5p