A probabilistic analysis of bias optimality in unichain Markov decision processes
ME Lewis, ML Puterman - IEEE Transactions on Automatic …, 2001 - ieeexplore.ieee.org
IEEE Transactions on Automatic Control, 2001•ieeexplore.ieee.org
Focuses on bias optimality in unichain, finite state, and action-space Markov decision
processes. Using relative value functions, we present methods for evaluating optimal bias,
this leads to a probabilistic analysis which transforms the original reward problem into a
minimum average cost problem. The result is an explanation of how and why bias implicitly
discounts future rewards.
processes. Using relative value functions, we present methods for evaluating optimal bias,
this leads to a probabilistic analysis which transforms the original reward problem into a
minimum average cost problem. The result is an explanation of how and why bias implicitly
discounts future rewards.
Focuses on bias optimality in unichain, finite state, and action-space Markov decision processes. Using relative value functions, we present methods for evaluating optimal bias, this leads to a probabilistic analysis which transforms the original reward problem into a minimum average cost problem. The result is an explanation of how and why bias implicitly discounts future rewards.
ieeexplore.ieee.org
以上显示的是最相近的搜索结果。 查看全部搜索结果