FAWAC adds a cost-advantage penalty to advantage weighted regression to keep offline-trained policies within a safety budget, with variants for standard and high-reward-but-unsafe datasets.
Maximum entropy inverse reinforcement learning in continuous state spaces with path integrals
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learning
FAWAC adds a cost-advantage penalty to advantage weighted regression to keep offline-trained policies within a safety budget, with variants for standard and high-reward-but-unsafe datasets.