Multi-policy test case selection (MPTCS) uses a set of policies to pick solvable, difficult, and diverse test cases that expose common flaws in any reinforcement learning policy.
Advances in Neural Information Processing Systems36, 45716–45743 (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reusable Test Suites for Reinforcement Learning
Multi-policy test case selection (MPTCS) uses a set of policies to pick solvable, difficult, and diverse test cases that expose common flaws in any reinforcement learning policy.