Constrained Flow Policy Updates: A Generalized Schr"odinger Bridge View
cs.LG, cs.RO
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies
- Generative Actor-Critic with Soft Bridge Policies
- FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance
- Boosting Maximum Entropy Reinforcement Learning via One-Step Flow Matching
- GeMPO: Generalized Measure Matching for Online Diffusion Reinforcement Learning
- Epigraph-Guided Flow Matching for Safe and Performant Offline Reinforcement Learning
- Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies
- Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching
- Flow Policy Gradients for Robot Control
- Truncated Rectified Flow Policy for Reinforcement Learning with One-Step Sampling
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