QAMM: Adjoint MeanFlow Matching for Few-Step Offline Reinforcement Learning
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning
- One-Step Flow Policy Mirror Descent
- Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
- Trust Region Q Adjoint Matching
- Scaling Offline RL via Efficient and Expressive Shortcut Models
- Mean Flows for One-step Generative Modeling
- Improved Mean Flows: On the Challenges of Fastforward Generative Models
- IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
- MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
- Q-learning with Adjoint Matching
- Much Ado About Noising: Dispelling the Myths of Generative Robotic Control
- Flow Q-Learning
- Diffusion Policies as an Expressive Policy Class for Offline 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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks