Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints
cs.LG
Submitted: 2026-03-18
Updated: 2026-10-21
Code: https://github.com/gtanaelle/FMER
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
- Adam: A Method for Stochastic Optimization
- Boosting Maximum Entropy Reinforcement Learning via One-Step Flow Matching
- Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies
- Flow Matching Policy Gradients
- Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
- Proximal Policy Optimization Algorithms
- Mirror Descent Policy Optimization
- Gymnasium: A Standard Interface for Reinforcement Learning Environments
- FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
- Policy Representation via Diffusion Probability Model for Reinforcement Learning
- Training Diffusion Policies via Prior-Mapping Co-Evolution
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