Open AccessA Sample-Efficient Algorithm for Episodic Finite-Horizon MDP with Constraints
Author(s) -
Krishna C. Kalagarla,
Rahul Jain,
Pierluigi Nuzzo
Publication year - 2021
Publication title -
proceedings of the ... aaai conference on artificial intelligence
Language(s) - English
Resource type - Journals
eISSN - 2374-3468
pISSN - 2159-5399
DOI - 10.1609/aaai.v35i9.16979
Subject(s) - markov decision process , time horizon , bellman equation , mathematical optimization , upper and lower bounds , correctness , horizon , successor cardinal , mathematics , linear programming , state (computer science) , function (biology) , state space , action (physics) , computer science , algorithm , markov process , statistics , mathematical analysis , physics , geometry , quantum mechanics , evolutionary biology , biology