Multi‐Armed Bandits and the Gittins Index
暂无分享,去创建一个
[1] K. Glazebrook. On a class of non-Markov decision processes , 1978, Journal of Applied Probability.
[2] K. Glazebrook. On the optimal allocation of two or more treatments in a controlled clinical trial , 1978 .
[3] L. Rodman. On the Many-armed Bandit Problem , 1978 .
[4] J. Gittins,et al. On Bayesian models in stochastic scheduling , 1977, Journal of Applied Probability.
[5] L. A. Klimko,et al. Bayesian rules for the two-armed bandit problem , 1977 .
[6] J. Gittins,et al. A hamiltonian approach to optimal stochastic resource allocation , 1977, Advances in Applied Probability.
[7] K. Glazebrook. Stochastic scheduling with order constraints , 1976 .
[8] K. Glazebrook. A profitability index for alternative research projects , 1976 .
[9] D. Blackwell. Discounted Dynamic Programming , 1965 .