Parameterized Diffusion Policy learns a behavior manifold to condition diffusion policies on low-dimensional continuous parameters, enabling interpolation between strategies and adaptation to novel constraints without policy weight updates.
Genpo: Generative diffusion models meet on-policy reinforcement learning.arXiv preprint arXiv:2505.18763
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
CGPO integrates training-free critic guidance into diffusion denoising to produce high-Q actions as regression targets, yielding SOTA results on MuJoCo locomotion and successful Franka arm grasping.
GenPO++ achieves exact Jacobian-free likelihood ratio computation for generative flow policies by embedding history states as auxiliary memory in a high-order reversible ODE solver.
Decentralized diffusion policies trained with importance sampling score matching enhance exploration and performance in cooperative MARL over Gaussian policy baselines.
citing papers explorer
-
From Noise to Control: Parameterized Diffusion Policies
Parameterized Diffusion Policy learns a behavior manifold to condition diffusion policies on low-dimensional continuous parameters, enabling interpolation between strategies and adaptation to novel constraints without policy weight updates.
-
Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance
CGPO integrates training-free critic guidance into diffusion denoising to produce high-Q actions as regression targets, yielding SOTA results on MuJoCo locomotion and successful Franka arm grasping.
-
GenPO++: Generative Policy Optimization with Jacobian-free Likelihood Ratios
GenPO++ achieves exact Jacobian-free likelihood ratio computation for generative flow policies by embedding history states as auxiliary memory in a high-order reversible ODE solver.
-
Decentralized Diffusion Policy Learning for Enhanced Exploration in Cooperative Multi-agent Reinforcement Learning
Decentralized diffusion policies trained with importance sampling score matching enhance exploration and performance in cooperative MARL over Gaussian policy baselines.