Bisimulation Metrics for Continuous Markov Decision Processes
From MaRDI portal
Publication:3225169
DOI10.1137/10080484XzbMath1253.39018OpenAlexW1995688924MaRDI QIDQ3225169
Prakash Panangaden, Norm Ferns, Doina Precup
Publication date: 15 March 2012
Published in: SIAM Journal on Computing (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1137/10080484x
linear programmingMarkov decision processreinforcement learningbisimulationmetricscontinuousstatistical sampling
Continuous-time Markov processes on general state spaces (60J25) Financial applications of other theories (91G80) Generation, random and stochastic difference and differential equations (37H10) Stability theory for difference equations (39A30) Stochastic difference equations (39A50)
Related Items
A pseudometric in supervisory control of probabilistic discrete event systems, Adaptive aggregation for reinforcement learning in average reward Markov decision processes, Explainability of probabilistic bisimilarity distances for labelled Markov chains, A taxonomy for similarity metrics between Markov decision processes, A Hemimetric Extension of Simulation for Semi-Markov Decision Processes, Mixed nondeterministic-probabilistic automata: blending graphical probabilistic models with nondeterminism, Pseudometrics for State Aggregation in Average Reward Markov Decision Processes, Dynamic Cheap Talk for Robust Adversarial Learning, Unnamed Item, Polynomial-time algorithms for computing distances of fuzzy transition systems, Probabilistic Model Checking of Labelled Markov Processes via Finite Approximate Bisimulations, Bisimulation for Markov Decision Processes through Families of Functional Expressions, Random Measurable Selections, Weak bisimulation is sound and complete for pCTL\(^*\), Unnamed Item, Unnamed Item, Long-term values in Markov decision processes, (co)algebraically, An algebraic approach for inferring and using symmetries in rule-based models, Bisimulation metrics and norms for real-weighted automata, Unnamed Item
