NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL

arXiv:2607.07855 · cs.LG · Submitted 2026-07-08 · Read on arXiv

cs.LG

Submitted: 2026-07-08

Updated: 2026-10-05

Code: https://github.com/erdemtbao/NFTR

Terminology

• Normalizing Flow — 2× in this paper · explained in 3 episodes
• Stochastic Dynamics — 2× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Failure Modes — 1× in this paper · explained in 3 episodes
• Mode Collapse — 1× in this paper · explained in 2 episodes
• Normalizing Flows — 1× in this paper · explained in 4 episodes
• Q-learning — 1× in this paper · explained in 3 episodes

Sources

• Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning
• NICE: Non-linear Independent Components Estimation
• Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning
• Data-Efficient Hierarchical Goal-Conditioned Reinforcement Learning via Normalizing Flows
• Normalizing Flows are Capable Models for Continuous Control
• Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning
• GCHR : Goal-Conditioned Hindsight Regularization for Sample-Efficient Reinforcement Learning
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
• Generative Trajectory Stitching through Diffusion Composition
• How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression
• Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making
• Test-Time Graph Search for Goal-Conditioned Reinforcement Learning
• Foundation Policies with Hilbert Representations
• Flow Q-Learning
• Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
• Goal-Conditioned Imitation Learning using Score-based Diffusion Policies
• Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
• Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policies
• Flattening Hierarchies with Policy Bootstrapping

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