DMRL: Document-Mediated Reinforcement Learning for Skill Optimization in Advertising Recommendation

arXiv:2609.02170 · cs.LG · Submitted 2026-09-02 · Read on arXiv

cs.LG

Submitted: 2026-09-02

Updated: 2026-09-02

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• GRPO — 12× in this paper · explained in 6 episodes
• Reinforcement Learning — 10× in this paper · explained in 4 episodes
• Ablation — 9× in this paper · explained in 1 episode
• Long-term Reward Predictor — 9× in this paper
• Two-stage training — 8× in this paper · explained in 2 episodes
• Two-Stage Training Strategy — 7× in this paper · explained in 3 episodes
• Ablation study — 6× in this paper · explained in 1 episode
• Dual-Relative Policy Optimization — 6× in this paper
• Agent Skills — 5× in this paper · explained in 1 episode
• Document-Mediated Reinforcement Learning — 5× in this paper
• Regularization — 5× in this paper · explained in 3 episodes
• Representation Learning — 5× in this paper · explained in 2 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Credit assignment — 4× in this paper · explained in 3 episodes
• AGN — 3× in this paper · explained in 1 episode
• Domain Adaptation — 3× in this paper · explained in 5 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• App Usage Duration — 2× in this paper
• Core — 2× in this paper · explained in 2 episodes
• Decoupling — 2× in this paper · explained in 2 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Life Time Value — 2× in this paper
• Posterior Expected Spend — 2× in this paper
• Temporal Fusion Transformer — 2× in this paper
• Transformer — 2× in this paper · explained in 2 episodes
• Adversarial Training — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Direct Preference Optimization (DPO) — 1× in this paper · explained in 9 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Group Relative Policy Optimization — 1× in this paper
• IEEE International Conference on Data Mining — 1× in this paper
• Information Leakage — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• KL Regularization — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Time Series Forecasting — 1× in this paper · explained in 3 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• EvoSkill: Automated Skill Discovery for Multi-Agent Systems
• Soft Adaptive Policy Optimization
• SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
• Tulu 3: Pushing Frontiers in Open Language Model Post-Training
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support
• Understanding R1-Zero-Like Training: A Critical Perspective
• SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
• Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
• Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
• AutoRefine: Compiling Trajectories into Validated Typed Agent Artifacts
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
• SkillX: Automatically Constructing Skill Knowledge Bases for Agents
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
• AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System Optimization
• SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
• SkillOpt: Executive Strategy for Self-Evolving Agent Skills

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