CLOOPD: Closing the Learner Loop in On-Policy Distillation
cs.LG
Submitted: 2026-09-21
Updated: 2026-09-21
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Trust-Region Behavior Blending for On-Policy Distillation
- What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
- $\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
- Proximal Policy Optimization Algorithms
- Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO
- Trust Region Policy Distillation
- Trust Region On-Policy Distillation
- When Should the Teacher Move? Temporal Coupling and Stability in Self On-Policy Distillation
- Qwen3 Technical Report
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- Distilling the Knowledge in a Neural Network
- OPD+: Rethinking the Advantage Design for On-Policy Distillation
- AsyncOPD: How Stale Can On-Policy Distillation Be?
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks