Travelled to:1 × United Kingdom
2 × USA
Collaborated with:A.Droniou F.Stulp T.Degris P.Wuillemin
Talks about:learn (2) autoencod (1) structur (1) reinforc (1) process (1) problem (1) weight (1) polici (1) matrix (1) markov (1)
Person: Olivier Sigaud
DBLP: Sigaud:Olivier
Contributed to:
201320122006Wrote 3 papers:
- ICML-c2-2013-AlainO
- Gated Autoencoders with Tied Input Weights (AD, OS), pp. 154–162.
- ICML-2012-StulpS #adaptation #matrix #policy
- Path Integral Policy Improvement with Covariance Matrix Adaptation (FS, OS), p. 201.
- ICML-2006-DegrisSW #learning #markov #problem #process
- Learning the structure of Factored Markov Decision Processes in reinforcement learning problems (TD, OS, PHW), pp. 257–264.