Constrained and Robust Policy Synthesis with Satisfiability-Modulo-Probabilistic-Model-Checking
"鲁棒策略" 相关文章
Multi-Environment POMDPs: Discrete Model Uncertainty Under Partial Observability
Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets
Efficient Solution and Learning of Robust Factored MDPs
