arXiv Machine Learning July 30, 2026 By Scott M. Norton

Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2607. 26059v1 Announce Type: new Abstract: We report a striking phenomenon: deep reinforcement learning agents trained with frozen, randomly initialized CNN feature extractors spontaneously develop extremely sparse fully-connected representations, without any sparsity-inducing objective.

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

Hugging Face Trending Papers

Jul 29

The Sparsity Ceiling: Where Spiking Networks Can and Cannot Trade Activity for Energy

Spiking neural networks (SNNs) are promoted as an energy-efficient substrate because sparse, event-driven activity replaces dense multiply-accumulates with cheap accumulates. We argue the energy dividend of sparsity is not a property of SNNs but of the task.

llms efficiency

arXiv Machine Learning

Jun 11

On the Stability of Growth in Structural Plasticity

arXiv:2605. 15435v2 Announce Type: replace Abstract: Standard deep-learning pipelines usually choose the network architecture before training and keep it fixed throughout optimization.

By Lute Lillo, Nick Cheney

efficiency benchmarks

arXiv AI

Jun 9

Structured Neuron Pruning in Deep Neural Networks Using Multi-Armed Bandits

arXiv:2606. 07615v1 Announce Type: cross Abstract: Deep neural networks often contain redundant hidden units.

By Salem Ameen, Sunil Vadera

reinforcement-learning efficiency benchmarks

arXiv Machine Learning

Aug 6

Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning

arXiv:2608. 05111v1 Announce Type: new Abstract: In partially observable reinforcement learning, agents face a dual bottleneck: they must explore to encounter rewarding states and retain that experience in memory to optimize their policies.

By Jai Malegaonkar, Rohan Patil, Henrik I. Christensen

agents reinforcement-learning efficiency

arXiv AI

Aug 3

Deconstructing Off-Policy Ratios: Entropy-Scaled Trust Regions for Asynchronous Reinforcement Learning

arXiv:2607. 22186v2 Announce Type: replace Abstract: Asynchronous reinforcement learning (RL) accelerates large language model (LLM) post-training by overlapping rollout generation with policy optimization, but the resulting stale, off-policy data can destabilize optimization and ultimately cause policy collapse.

By Guanqun Zhao, Zijun Xie, Binbin Zheng, Enlei Gong, Jiafeng Lu, Yehan Yang, Aoqi Hu, Zeyu Chen

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 17

NORACL: Neurogenesis for Oracle-free Resource-Adaptive Continual Learning

arXiv:2604. 27031v2 Announce Type: replace-cross Abstract: In a continual learning setting, we require a model to be plastic enough to learn a new task and stable enough to not disturb previously learned capabilities.

By Karthik Charan Raghunathan, Christian Metzner, Laura Kriener, Melika Payvand

Related stories

The Sparsity Ceiling: Where Spiking Networks Can and Cannot Trade Activity for Energy

On the Stability of Growth in Structural Plasticity

Structured Neuron Pruning in Deep Neural Networks Using Multi-Armed Bandits

Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning

Deconstructing Off-Policy Ratios: Entropy-Scaled Trust Regions for Asynchronous Reinforcement Learning

NORACL: Neurogenesis for Oracle-free Resource-Adaptive Continual Learning