Abstract | ||
---|---|---|
This paper considers a Markov decision process (MDP) model with safety state constraints, which specify polytopic invariance constraints on the state probability distribution (pd) for all time epochs. Typically, in the MDP framework, safety is addressed indirectly by penalizing failure states through the reward function. However, such an approach does not allow imposing hard constraints on the sta... |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TAC.2018.2849556 | IEEE Transactions on Automatic Control |
Keywords | Field | DocType |
Dynamic programming,Markov processes,Probability distribution,Decision making,Linear programming,Decision theory | Mathematical optimization,Markov process,Invariant (physics),Control theory,Upper and lower bounds,Duality (mathematics),Markov decision process,Probability distribution,Linear programming,Convex optimization,Mathematics | Journal |
Volume | Issue | ISSN |
64 | 3 | 0018-9286 |
Citations | PageRank | References |
4 | 0.43 | 8 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mahmoud El Chamie | 1 | 42 | 7.18 |
Yue Yu | 2 | 219 | 29.56 |
Behçet Açikmese | 3 | 41 | 15.88 |
Masahiro Ono | 4 | 133 | 14.40 |