Beyond Expected Values: Risk-Sensitive Planning with Distributional Monte-Carlo Tree Search
Experiments on stochastic planning benchmarks show that distributional Q-edges improve lower-tail return and reduce catastrophic outcomes when mean-optimal and risk-sensitive behavior differ, and two distributional MCTS algorithms that maintain finite-support empirical backup laws at Q-edges are introduced.
Q. Trinh, Trung Nguyen, N. Nguyen et al.
· 0 citations