14 papers:
TACAS-2015-BrazdilCFK #multi #named #synthesis- MultiGain: A Controller Synthesis Tool for MDPs with Multiple Mean-Payoff Objectives (TB, KC, VF, AK), pp. 181–187.
ICML-c2-2014-ScholzLIW #object-oriented- A Physics-Based Model Prior for Object-Oriented MDPs (JS, ML, CLIJ, DW), pp. 1089–1097.
- ICML-c2-2014-TamarMX #approximate #robust #scalability #using
- Scaling Up Robust MDPs using Function Approximation (AT, SM, HX), pp. 181–189.
RecSys-2014-TavakolB #detection #topic- Factored MDPs for detecting topics of user sessions (MT, UB), pp. 33–40.
CAV-2013-PuggelliLSS #nondeterminism #polynomial #verification- Polynomial-Time Verification of PCTL Properties of MDPs with Convex Uncertainties (AP, WL, ALSV, SAS), pp. 527–542.
- ICML-2012-GrunewalderLBPG #modelling
- Modelling transition dynamics in MDPs with RKHS embeddings (SG, GL, LB, MP, AG), p. 208.
- ICML-2012-MannorMX #nondeterminism #robust
- Lightning Does Not Strike Twice: Robust MDPs with Coupled Uncertainty (SM, OM, HX), p. 62.
ICALP-v2-2011-BrazdilBEK #approximate #game studies #probability #termination- Approximating the Termination Value of One-Counter MDPs and Stochastic Games (TB, VB, KE, AK), pp. 332–343.
- ICML-2011-ChakrabortyS #learning
- Structure Learning in Ergodic Factored MDPs without Knowledge of the Transition Function’s In-Degree (DC, PS), pp. 737–744.
- ICML-2010-KrishnamurthyT
- Inverse Optimal Control with Linearly-Solvable MDPs (KD, ET), pp. 335–342.
- ICML-2009-SzitaL #learning #polynomial
- Optimistic initialization and greediness lead to polynomial time learning in factored MDPs (IS, AL), pp. 1001–1008.
- ICML-2007-OsentoskiM #learning
- Learning state-action basis functions for hierarchical MDPs (SO, SM), pp. 705–712.
- ICML-2005-JonssonB #approach #composition
- A causal approach to hierarchical decomposition of factored MDPs (AJ, AGB), pp. 401–408.
- ICML-2002-GuestrinPS #learning #modelling
- Algorithm-Directed Exploration for Model-Based Reinforcement Learning in Factored MDPs (CG, RP, DS), pp. 235–242.
