mlsanityData to 14 Oct 2026

Silent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adaptive Video Streaming

arXiv 2505.01584 ↗First posted 2 May 2025cs.LG cs.AIcited by 1

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Adaptive video streaming optimizes Quality of Experience (QoE) metrics by selecting appropriate bitrates according to varying network bandwidth and user demands. In practice, however, real-world network bandwidth often exhibits heterogeneity relative to training environments. Current methods predominantly tackle this problem through learning-based approaches designed to improve generalization performance. While our systematic investigation reveals a critical limitation: neural networks suffer from plasticity loss, significantly impeding their ability to adapt to heterogeneous network conditions. Through theoretical analysis of neural propagation mechanisms, we demonstrate that existing dormant neuron metrics inadequately characterize neural plasticity loss. To address this limitation, we have developed the Silent Neuron theory, which provides a more comprehensive framework for understanding plasticity degradation. Based on these theoretical insights, we propose the Reset Silent Neuron (ReSiN), which preserves neural plasticity through strategic neuron resets guided by both forward and backward propagation states. Moreover, we establish a tighter performance bound for ReSiN under non-stationary network conditions. In our implementation of an adaptive video streaming system, ReSiN has shown significant improvements over existing solutions, achieving up to 168% higher bitrate and 108% better quality of experience (QoE) while maintaining comparable smoothness. Furthermore, ReSiN consistently outperforms in stationary environments, demonstrating its robust adaptability across different network conditions.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 26 of its 57 references that are in the map. First posted on arXiv 2 May 2025.

Builds on

26 of 57 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Knowledge Retention for Continual Model-Based Reinforcement Learning6 Mar
  2. 2024Neuroplastic Expansion in Deep Reinforcement Learning10 Oct
  3. 2024Normalization and effective learning rates in reinforcement learning1 Jul
  4. 2024Weight Clipping for Deep Continual and Reinforcement Learning1 Jul
  5. 2024A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning29 May
  6. 2024Disentangling the Causes of Plasticity Loss in Neural Networks29 Feb

Other references · 20

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015Trust Region Policy Optimizationcited by 2,580
  3. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  4. 2015Train faster, generalize better: Stability of stochastic gradient descentcited by 552
  5. 2018How Does Batch Normalization Help Optimization?cited by 357
  6. 2023The Dormant Neuron Phenomenon in Deep Reinforcement Learningcited by 174
  7. 2023Understanding plasticity in neural networkscited by 174
  8. 2023A Definition of Continual Reinforcement Learningcited by 101
  9. 2020Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimismcited by 76
  10. 2023Deep Reinforcement Learning with Plasticity Injectioncited by 74
  11. 2023Maintaining Plasticity in Continual Learning via Regenerative Regularizationcited by 65
  12. 2023DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimizationcited by 47
8 more
  1. 2024Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networkscited by 43
  2. 2016BOLA: Near-Optimal Bitrate Adaptation for Online Videoscited by 27
  3. 2023Directions of Curvature as an Explanation for Loss of Plasticitycited by 26
  4. 2022An Empirical Study of Implicit Regularization in Deep Offline RLcited by 24
  5. 2022CausalSim: A Causal Framework for Unbiased Trace-Driven Simulationcited by 10
  6. 2023MANSY: Generalizing Neural Adaptive Immersive Video Streaming With Ensemble and Representation Learningcited by 5
  7. 2024An End-to-End Pipeline Perspective on Video Streaming in Best-Effort Networks: A Survey and Tutorialcited by 4
  8. 2025Plasticity-Aware Mixture of Experts for Learning Under QoE Shifts in Adaptive Video Streamingcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026PRIME: Plasticity Recovery in Multi-Agent Environments for UAV-Assisted Emergency Communication Networkscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning
  2. 2026Rethinking Plasticity in Deep Reinforcement Learning
  3. 2025Preserving Plasticity in Continual Learning with Adaptive Linearity Injection
  4. 2025AltNet: Addressing the Plasticity-Stability Dilemma in Reinforcement Learning
  5. 2024Plasticity Loss in Deep Reinforcement Learning: A Survey
  6. 2025Mastering Continual Reinforcement Learning through Fine-Grained Sparse Network Allocation and Dormant Neuron Exploration
  7. 2026Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning
  8. 2024EVAN: Evolutional Video Streaming Adaptation via Neural Representation