Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Regret Guarantees for Linear Contextual Stochastic Shortest Path
Dor Polikar, Alon Cohen
We define the problem of linear Contextual Stochastic Shortest Path (CSSP), where at the beginning of each episode, the learner observes an adversarially chosen context that determ…
cs.GT2025
Playing Markov Games Without Observing Payoffs
Daniel Ablin, Alon Cohen
Optimization under uncertainty is a fundamental problem in learning and decision-making, particularly in multi-agent systems. Previously, Feldman, Kalai, and Tennenholtz [2010] dem…