Research map / Reinforcement learning / Visual and representation RL
DEAR: Deep Reinforcement Learning for Online Advertising Impression in Recommender Systems
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DEAR's joint ad, location, and insertion decision instead of HDQN | Online advertising in recommender systems · Douyin simulated online environment | accumulated reward: 10.27 -> 10.96 | Helped |
| Use reinforcement learning instead of supervised learning (ablation) | DEAR · Douyin simulated online environment | accumulated reward: 9.936 -> 10.96 | Helped |
| Use recurrent networks to capture users' sequential preferences (ablation) | DEAR · Douyin simulated online environment | accumulated reward: 10.02 -> 10.96 | Helped |
| Use DEAR's joint ad-and-location Q-network rather than a conventional DQN with location input (ablation) | DEAR · Douyin simulated online environment | accumulated reward: 10.39 -> 10.96 | Helped |
| Factor the Q-function into state value and state-action advantage (ablation) | DEAR · Douyin simulated online environment | accumulated reward: 10.57 -> 10.96 | Helped |
| Select an appropriate ad rather than a random candidate ad (ablation) | DEAR · Douyin simulated online environment | accumulated reward: 9.735 -> 10.96 | Helped |
| Select an appropriate slot rather than a random slot (ablation) | DEAR · Douyin simulated online environment | accumulated reward: 9.963 -> 10.96 | Helped |
| Increase the user-experience weight alpha | DEAR reward function · Douyin simulated online environment | ad revenue | Hurt |
| Increase the user-experience weight alpha | DEAR reward function · Douyin simulated online environment | user-experience reward | Helped |
Closest papers by meaning
- On the Unexpected Effectiveness of Reinforcement Learning for Sequential Recommendation (ICML 2024 · similarity 0.86)
- The Adaptive Q-Network for Recommendation Tasks with Dynamic Item Space (AAAI 2025 · similarity 0.85)
- Contrastive Representation for Interactive Recommendation (AAAI 2025 · similarity 0.84)
- Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders (NeurIPS 2026 · similarity 0.84)
- UNEX-RL: Reinforcing Long-Term Rewards in Multi-Stage Recommender Systems with UNidirectional EXecution (AAAI 2024 · similarity 0.83)
- AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games (NeurIPS 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.