Diffusion Policy Improvement with Proposal-Conditioned Refinement Flows
cs.LG, cs.AI, cs.RO
Submitted: 2026-09-29
Updated: 2026-10-01
Terminology
Sources
- FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning
- Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models
- Fisher Decorator: Refining Flow Policy via a Local Transport Map
- Trust Region Q Adjoint Matching
- Entropy-Regularized Adjoint Matching for Offline Reinforcement Learning
- IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
- FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance
- Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone
- DeFlow: Decoupling Manifold Modeling and Value Maximization for Offline Policy Extraction
- AWAC: Accelerating Online Reinforcement Learning with Offline Datasets
- Reversal Q-Learning
- QPILOTS: Efficient Test-Time Q-Steering for Flow Policies
- Efficient Adjoint Matching for Fine-tuning Diffusion Models
- Residual Policy Learning
- Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching
- Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks