排序方式: 共有2条查询结果,搜索用时 15 毫秒
1
1.
This paper concerns a Markov operator T on a space L1, and aMarkov process P which defines a Markov operator on a spaceM of finite signed measures. For T, the paper presents necessaryand sufficient conditions for:
- a the existence of invariant probabilitydensities (IPDs)
- b the existence of strictly positive IPDs,and
- c the existence and uniqueness of IPDs.
- b the existence of strictly positive IPDs,and
2.
Recent results for parameter-adaptive Markov decision processes (MDP's) are extended to partially observed MDP's depending on unknown parameters. These results include approximations converging uniformly to the optimal reward function and asymptotically optimal adaptive policies.This research was supported in part by the Consejo del Sistema Nacional de Educación Tecnologica (COSNET) under Grant 178/84, in part by the Air Force Office of Scientific Research under Grant AFOSR-84-0089, in part by the National Science Foundation under Grant ECS-84-12100, and in part by the Joint Services Electronics Program under Contract F49602-82-C-0033. 相似文献
1