Travelled to:1 × France
2 × China
Collaborated with:S.Mannor D.J.Mankowitz A.Hallak F.Schnitzler
Talks about:polici (2) option (2) iter (2) interrupt (1) approxim (1) unknown (1) regular (1) factor (1) better (1) under (1)
Person: Timothy Arthur Mann
DBLP: Mann:Timothy_Arthur
Contributed to:
201520142014Wrote 3 papers:
- ICML-2015-HallakSMM #learning #modelling
- Off-policy Model-based Learning under Unknown Factored Dynamics (AH, FS, TAM, SM), pp. 711–719.
- ICML-c1-2014-MannM #approximate #policy #scalability
- Scaling Up Approximate Value Iteration with Options: Better Policies with Fewer Iterations (TAM, SM), pp. 127–135.
- ICML-c2-2014-MannMM
- Time-Regularized Interrupting Options (TRIO) (TAM, DJM, SM), pp. 1350–1358.