Hugging Face Trending Papers
Value-Guided Repulsion for Offline Reinforcement Learning
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv AI
Jul 24
Expert Behavior Prior Reinforcement Learning
arXiv:2607. 21302v1 Announce Type: new Abstract: Behavior prior reinforcement learning (BPRL) has emerged as a promising paradigm to improve sample efficiency in online reinforcement learning (RL) by leveraging policy priors derived from offline demonstrations.
arXiv AI
Jun 2
Drift Q-Learning
arXiv:2606. 00350v1 Announce Type: cross Abstract: Offline reinforcement learning requires improving a policy from fixed data while avoiding out-of-distribution actions with unreliable value estimates.
arXiv AI
6d ago
Sample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors
The paper introduces AnchorQ, a method that improves sample-efficient reinforcement learning for policy refinement by using flow-reversed action anchors. AnchorQ maps reference behaviors to state-conditioned latent anchors, samples local particles around these anchors, and employs value-guided sampling to explore promising refinements. Experiments on simulated and real-world manipulation tasks show that AnchorQ outperforms state-of-the-art post-training baselines, achieving a 37% higher real-world success rate and 97% greater simulated task throughput within the same interaction budget.
arXiv Machine Learning
Aug 26
CoDrift: Compositional Drifting for Offline Reinforcement Learning
arXiv:2608.23939v1 Announce Type: new Abstract: Offline reinforcement learning is intrinsically multi-objective: a policy must remain compatible with the behavioral support of a fixed dataset while p...
arXiv AI
Oct 2
DriftOPD: Sequence-Level Reverse-KL Distillation for One-Step VLA Policies
DriftOPD is a teacher‑free, rollout‑free framework that performs sequence‑level on‑policy distillation of continuous Vision‑Language‑Action (VLA) action experts. It decomposes the sequence‑level reverse‑KL divergence into a chunk‑level reverse‑KL term and a future‑potential term, optimizing them with a one‑step drifting objective and a Q‑function critic learned from offline demonstrations. Experiments on multiple VLA architectures in simulation and real‑world manipulation show that DriftOPD outperforms existing one‑step distillation baselines while matching the task success of multi‑step teacher policies.
arXiv Machine Learning
Jul 9
Latent Policy Steering through One-Step Flow Policies
arXiv:2603. 05296v2 Announce Type: replace-cross Abstract: Offline reinforcement learning (RL) allows robots to learn from offline datasets without risky exploration.