Login / Signup
Time is Budget: A Heuristic for Reducing the Risk of Ruin in Multi-armed Gambler Bandits.
Filipo Studzinski Perotto
Xavier Pucel
Jean-Loup Farges
Published in:
SGAI Conf. (2022)
Keyphrases
</>
optimal solution
constraint satisfaction
dynamic programming
simulated annealing
greedy heuristic
risk assessment
search procedure
lower bound
reinforcement learning
combinatorial optimization
solution quality
e learning
decision making
packing problem
high risk
risk analysis
data sets