SDGD uses cost-conditioned classifier-free guidance plus reward guidance with feasible trajectory relabeling to generate safe high-reward trajectories that adapt to changing safety budgets in offline RL.
Beyond hard constraints: Budget-conditioned reachability for safe offline reinforcement learning.arXiv preprint arXiv:2603.22292
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning
SDGD uses cost-conditioned classifier-free guidance plus reward guidance with feasible trajectory relabeling to generate safe high-reward trajectories that adapt to changing safety budgets in offline RL.