Travelled to:
2 × USA
Collaborated with:
∅
Talks about:
bayesian (1) approxim (1) problem (1) markov (1) diffus (1) design (1) bandit (1) probe (1) optim (1) learn (1)
Person: Michael O. Duff
DBLP: Duff:Michael_O=
Contributed to:
Wrote 3 papers:
- ICML-2003-Duff #design
- Design for an Optimal Probe (MOD), pp. 131–138.
- ICML-2003-Duff03a #approximate #markov
- Diffusion Approximation for Bayesian Markov Chains (MOD), pp. 139–146.
- ICML-1995-Duff #problem
- Q-Learning for Bandit Problems (MOD), pp. 209–217.