arXiv Machine Learning
Jul 7
RL Forgets! Towards Continual Policy Optimization
arXiv:2607. 04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.
REDAR: Reinforcement-Driven Adaptive Regularisation for Class Incremental Learning
Related stories
arXiv Machine Learning
Sep 18
Improving Online Reinforcement Learning via Bidirectional Behavior Prior Distillation
The paper introduces Bidirectional Behavior Prior Distillation (B2PD), a method that uses action‑value priors to train a conditional variational autoencoder for generating high‑value behavior support. These expert behavior priors are then distilled into the online reinforcement learning agent, reducing inefficient exploration and stabilizing policy updates. Experiments on state‑ and pixel‑based tasks show that B2PD improves sample efficiency while maintaining stable learning dynamics.
arXiv AI
Jun 8
Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
arXiv:2601. 18510v2 Announce Type: replace-cross Abstract: While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights after deployment.
arXiv Machine Learning
Sep 21
REFINEPPO: Learning Continuous Control Policies by Iterative Action Refinement
arXiv:2609.21108v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) has achieved strong performance across a wide range of continuous-control problems. These continuous-control policies...
arXiv AI
1d ago
Permanent and Transient Representations for Continual Reinforcement Learning
arXiv:2611.07327v1 Announce Type: cross Abstract: Continual Reinforcement Learning (CRL) agents struggle to adapt to new situations while retaining prior knowledge, leading to a stability-plasticity...
arXiv Machine Learning
Oct 23
What Does It Take For A Generalist Robot Policy To Adapt Using Minimal Data?
The paper introduces a minimal‑data adaptation regime where a pretrained robot policy learns a new task from a single demonstration followed by autonomous online interaction. It shows that while zero‑shot performance is poor, one demonstration can guide the policy toward coarse task‑following, and identifies key design principles—pretrained VLA representations for sample‑efficient value learning, residual policy learning for corrective behavior, and data‑balancing to avoid exploration collapse. The proposed MiDAS method, combining few‑demonstration behavior cloning with value‑based residual learning over frozen VLA representations, significantly boosts task success on LIBERO, RoboCasa, and a bimanual YAM platform after only a few hours of online interaction.
arXiv Machine Learning
Jun 2
Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
arXiv:2603. 11653v2 Announce Type: replace Abstract: Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that can adapt in openended, evolving environments.
arXiv AI
Jul 23
REGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning
arXiv:2607. 19450v1 Announce Type: cross Abstract: Large-scale online reinforcement learning (RL) is the predominant means of eliciting advanced abilities including long-term reasoning and agentic tool use in large language models (LLMs).
Hugging Face Trending Papers
Oct 5
Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning
The paper demonstrates that off‑policy merging, called grafting, outperforms on‑policy self‑distillation for continual learning. Grafting learns updates on an earlier donor checkpoint, scales the update, and optionally masks sensitive directions, thereby reducing interference with existing capabilities. Across various continual learning scenarios, grafting achieves better new‑task and old‑task performance without costly on‑policy sampling.
arXiv AI
Jul 8
To Retain or to Adapt? Generalizing Continual Learning
arXiv:2607. 05609v1 Announce Type: cross Abstract: The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting.
arXiv AI
Aug 11
The Cell Must Go On: Agar.io for Continual Reinforcement Learning
arXiv:2505. 18347v3 Announce Type: replace-cross Abstract: Continual reinforcement learning (RL) concerns agents that are expected to learn continually, rather than converge to a policy that is then fixed for evaluation.
arXiv Machine Learning
Jun 9
Theoretical Foundations of Continual Learning via Drift-Plus-Penalty
arXiv:2606. 08452v1 Announce Type: new Abstract: In many real-world settings, data streams are nonstationary and arrive sequentially, requiring learning systems to adapt continuously without retraining from scratch.