Travelled to:1 × China
1 × France
Collaborated with:E.Eaton R.Tutunov P.Ruvolo M.E.Taylor
Talks about:polici (2) learn (2) sublinear (1) reinforc (1) lifelong (1) gradient (1) search (1) regret (1) method (1) onlin (1)
Person: Haitham Bou-Ammar
DBLP: Bou-Ammar:Haitham
Contributed to:
20152014Wrote 2 papers:
- ICML-2015-Bou-AmmarTE #learning #policy #sublinear
- Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret (HBA, RT, EE), pp. 2361–2369.
- ICML-c2-2014-Bou-AmmarERT #learning #multi #online #policy
- Online Multi-Task Learning for Policy Gradient Methods (HBA, EE, PR, MET), pp. 1206–1214.