Travelled to:1 × China
1 × France
1 × USA
1 × United Kingdom
Collaborated with:V.Koltun J.Schulman P.Abbeel M.I.Jordan P.Moritz
Talks about:optim (4) polici (3) trajectori (1) network (1) control (1) continu (1) complex (1) search (1) region (1) neural (1)
Person: Sergey Levine
DBLP: Levine:Sergey
Contributed to:
2015201420132012Wrote 4 papers:
- ICML-2015-SchulmanLAJM #optimisation #policy #trust
- Trust Region Policy Optimization (JS, SL, PA, MIJ, PM), pp. 1889–1897.
- ICML-c2-2014-LevineK #learning #network #optimisation #policy
- Learning Complex Neural Network Policies with Trajectory Optimization (SL, VK), pp. 829–837.
- ICML-c3-2013-LevineK #policy
- Guided Policy Search (SL, VK), pp. 1–9.
- ICML-2012-LevineK
- Continuous Inverse Optimal Control with Locally Optimal Examples (SL, VK), p. 65.