2 papers
cs.LG2026
When Does Non-Uniform Replay Matter in Reinforcement Learning?
Michal Korniak, MikoÅaj Czarnecki, Yarden As +3
Modern off-policy reinforcement learning algorithms often rely on simple uniform replay sampling and it remains unclear when and why non-uniform replay improves over this strong ba…
cs.GT2026
Fair Indivisible Payoffs through Shapley Value
MikoÅaj Czarnecki, MichaÅ Korniak, Oskar Skibski +1
We consider the problem of payoff division in indivisible coalitional games, where the value of the grand coalition is a natural number. This number represents a certain quantity o…