arXiv Machine Learning June 11, 2026 By Felix St\"orck, Fabian Hinder, Barbara Hammer

Space-sampled Value Decay: Forgetting Mechanisms for Non-stationary Deep Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2606. 11797v1 Announce Type: new Abstract: Studies on rodents such as mice have shown the capabilities to adapt their behavior when dealing with changing parameters (``drift'') of the environment even if no information about change is provided (uncertainty) -- a behavior that can be modeled by forgetting mechanisms.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 5

Enhancing Q-Value Updates in Deep Q-Learning via Successor-State Prediction

arXiv:2511. 03836v2 Announce Type: replace Abstract: Deep Q-Networks (DQNs) estimate future returns by learning from transitions sampled from a replay buffer.

By Lipeng Zu, Hansong Zhou, Xiaonan Zhang

agents reinforcement-learning benchmarks

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.

By Mao-Lin Luo, Zhe-Xu Wang, Zi-Hao Zhou, Bo Ye, Jian Zhao, Min-Ling Zhang, Tong Wei

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jun 12

ARROW: Augmented Replay for RObust World models

arXiv:2603. 11395v3 Announce Type: replace-cross Abstract: Continual reinforcement learning challenges agents to acquire new skills while retaining previously learned ones with the goal of improving performance in both past and future tasks.

By Abdulaziz Alyahya, Abdallah Al Siyabi, Markus R. Ernst, Luke Yang, Levin Kuhlmann, Gideon Kowadlo

agents reinforcement-learning

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.

By Anas Houssaini, Mohamad H. Danesh, Amin Abyaneh, Scott Fujimoto, Hsiu-Chin Lin, David Meger

diffusion reinforcement-learning efficiency data-engineering

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.

By Jiaheng Hu, Jay Shim, Chen Tang, Yoonchang Sung, Bo Liu, Peter Stone, Roberto Martin-Martin

agents reinforcement-learning robotics fine-tuning multimodal benchmarks

arXiv Machine Learning

Jul 10

When Does Continual Learning Require Learning

arXiv:2607. 07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn?

By Anne Harrington, Nayan Saxena, Michael Murphy, Anastasia Borovykh, Zeyu Yun, Sridhar Kamath, Ara Eindra Kyi, Trevor Darrell, Jitendra Malik, Yutong Bai

llms agents reinforcement-learning fine-tuning efficiency benchmarks

Related stories

Enhancing Q-Value Updates in Deep Q-Learning via Successor-State Prediction

RL Forgets! Towards Continual Policy Optimization

ARROW: Augmented Replay for RObust World models

Drift Q-Learning

Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning

When Does Continual Learning Require Learning