The paper introduces an inductive synthesis framework that generates verifiable deterministic program approximations of neural RL policies, preserving safety invariants via counterexample-guided search over state transition systems.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2019 2verdicts
UNVERDICTED 2representative citing papers
DEMER reconstructs recommendation environments with hidden confounders by treating them as hidden policies in a multi-agent GAIL framework, yielding improved policies on driver program recommendation tasks.
citing papers explorer
-
An Inductive Synthesis Framework for Verifiable Reinforcement Learning
The paper introduces an inductive synthesis framework that generates verifiable deterministic program approximations of neural RL policies, preserving safety invariants via counterexample-guided search over state transition systems.
-
Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation
DEMER reconstructs recommendation environments with hidden confounders by treating them as hidden policies in a multi-agent GAIL framework, yielding improved policies on driver program recommendation tasks.