Flow matching critics outperform monolithic ones in RL by 2x performance and 5x sample efficiency via test-time error recovery through integration and multi-point velocity supervision that preserves feature plasticity.
Deep reinforcement learning with plasticity injection.Advances in Neural Information Processing Systems, 36:37142–37159, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
What Does Flow Matching Bring To TD Learning?
Flow matching critics outperform monolithic ones in RL by 2x performance and 5x sample efficiency via test-time error recovery through integration and multi-point velocity supervision that preserves feature plasticity.