BDPO computes the behavior-regularization penalty for diffusion policies as a sum of per-denoising-step KL divergences and optimizes with a two-time-scale actor-critic, achieving strong D4RL performance.
Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning
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
-
Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning
BDPO computes the behavior-regularization penalty for diffusion policies as a sum of per-denoising-step KL divergences and optimizes with a two-time-scale actor-critic, achieving strong D4RL performance.