First Page | Document Content | |
---|---|---|
Date: 2015-02-02 16:39:01Markov processes Probability theory Probability Dynamic programming Markov decision process Stochastic control Reinforcement learning Memorylessness | MultiGain: A controller synthesis tool for MDPs with multiple mean-payoff objectives Tom´ aˇs Br´ azdil1, Krishnendu Chatterjee2 , Vojtˇech Forejt3 , and Anton´ın Kuˇcera1 1Add to Reading ListSource URL: qav.comlab.ox.ac.ukDownload Document from Source WebsiteFile Size: 370,21 KBShare Document on Facebook |