Computing Fixpoints of Learned Functions: Chaotic Iteration and Simple Stochastic Games
Published in TACAS, 2026
An significant generalization of the results from the CAV paper, including results for stochastic games, chaotic iteration, and generalizations of convergence results for purely model-based reinforcement learning algorithms.
Recommended citation: Baldan, P., Gurke, S., König, B., Wittbold, F. (2026). Computing Fixpoints of Learned Functions: Chaotic Iteration and Simple Stochastic Games. In: Junges, S., Katz, G. (eds) Tools and Algorithms for the Construction and Analysis of Systems. TACAS 2026. Lecture Notes in Computer Science, vol 16505. Springer, Cham.
Download Paper | Download Slides | Download Bibtex
