DROL trains one-step offline RL actors via top-1 dynamic routing of dataset actions to latent candidates, enabling local improvements while preserving data support and retaining cheap inference.
Scaling offline rl via efficient and expressive shortcut models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 5years
2026 5roles
background 1polarities
background 1representative citing papers
DFP is a one-step generative policy using Wasserstein gradient flow on a drifting model backbone, with a top-K behavior cloning surrogate, that reaches SOTA on Robomimic and OGBench manipulation tasks.
PROCO generates synthetic unsafe samples via model-based rollouts and LLM-grounded costs to enable safer policy learning from offline datasets containing few or no violations.
Flow matching critics outperform monolithic ones in RL by 2x performance and 5x sample efficiency via test-time error recovery through integration and multi-point velocity supervision that preserves feature plasticity.
citing papers explorer
-
Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning
DROL trains one-step offline RL actors via top-1 dynamic routing of dataset actions to latent candidates, enabling local improvements while preserving data support and retaining cheap inference.
-
Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow
DFP is a one-step generative policy using Wasserstein gradient flow on a drifting model backbone, with a top-K behavior cloning surrogate, that reaches SOTA on Robomimic and OGBench manipulation tasks.
-
Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data
PROCO generates synthetic unsafe samples via model-based rollouts and LLM-grounded costs to enable safer policy learning from offline datasets containing few or no violations.
-
What Does Flow Matching Bring To TD Learning?
Flow matching critics outperform monolithic ones in RL by 2x performance and 5x sample efficiency via test-time error recovery through integration and multi-point velocity supervision that preserves feature plasticity.
- Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning