MinSubFI directly minimizes subdominance, a margin-based measure of failing to be acceptable, and empirically reports higher demonstrator acceptability than prior imitation methods.
Deep reinforcement learning from human preferences.Ad- vances in Neural Information Processing Systems , 30,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Imitation Learning via Focused Satisficing
MinSubFI directly minimizes subdominance, a margin-based measure of failing to be acceptable, and empirically reports higher demonstrator acceptability than prior imitation methods.