Non-parametric closed-form bounds on counterfactual MDP transitions across compatible causal models, supporting robust policy optimization under interval uncertainty.
We can define a so-calledcounterfactual MDP M𝜏 by solving the SCM (8) for each transition along an observed path 𝜏 in an MDP M
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust Counterfactual Inference in Markov Decision Processes
Non-parametric closed-form bounds on counterfactual MDP transitions across compatible causal models, supporting robust policy optimization under interval uncertainty.