Efficient PAC learning for episodic tasks with acyclic state spaces
From MaRDI portal
Publication:2465672
DOI10.1007/s10626-007-0014-3zbMath1137.90021MaRDI QIDQ2465672
Theologos Bountourelis, Spyros A. Reveliotis
Publication date: 7 January 2008
Published in: Discrete Event Dynamic Systems (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s10626-007-0014-3
Markov decision processes; Computational learning theory; Machine learning; Uncertainty management; Efficient probably approximately correct (PAC) algorithms; Ranking \& selection
68T05: Learning and adaptive systems in artificial intelligence
93C41: Control/observation systems with incomplete information
93C65: Discrete event control/observation systems
90C40: Markov and semi-Markov decision processes
Related Items
Optimal flow control in acyclic networks with uncontrollable routings and precedence constraints, Optimal node visitation in acyclic stochastic digraphs with multi-threaded traversals and internal visitation requirements, Efficient PAC learning for episodic tasks with acyclic state spaces
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Near-optimal reinforcement learning in polynomial time
- Efficient PAC learning for episodic tasks with acyclic state spaces
- Probability Inequalities for Sums of Bounded Random Variables
- A Single-Sample Multiple Decision Procedure for Ranking Means of Normal Populations with known Variances