Silent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adaptive Video Streaming
cs.LG, cs.AI
Submitted: 2025-05-02
Updated: 2026-11-11
Terminology
Sources
- SABR: A Stable Adaptive Bitrate Framework Using Behavior Cloning Pretraining and Reinforcement Learning Fine-Tuning
- Proximal Policy Optimization Algorithms
- A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
- Neuroplastic Expansion in Deep Reinforcement Learning
- Disentangling the Causes of Plasticity Loss in Neural Networks
- Directions of Curvature as an Explanation for Loss of Plasticity
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis