Research map / Reinforcement learning / MDPs and planning
Weakly Coupled Deep Q-Networks
Ibrahim El Shar, Daniel R. Jiang
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add Lagrangian upper-bound projection step to tabular Q-learning (WCQL vs Lagrangian QL) (ablation) | WCQL · EV charging deadline scheduling | mean episode total reward | Improved |
| add projection step to Q-learning with bounds (WCQL vs standard Q-learning) | WCQL · EV charging deadline scheduling | relative error of value function | Improved |
| replace Q-learning/Double-QL/SQL/BCQL baselines with WCQL | tabular Q-learning · EV charging deadline scheduling | mean episode total reward | Improved |
| use WCDQN instead of DQN, Double DQN and OTDQN | DQN · Multi-product inventory control (N=10) | mean total reward | Improved |
| use WCDQN instead of DQN, Double DQN and OTDQN | DQN · Online stochastic ad matching (N=6) | mean total reward | Improved |
| use WCQL vs Lagrangian QL late in training (ablation) | WCQL · EV charging deadline scheduling | mean episode total reward | No clear effect |
Closest papers by meaning
- Convergent and Efficient Deep Q Learning Algorithm (ICLR 2022 · similarity 0.87)
- Universal Approximation Theorem of Deep Q-Networks (ICML 2025 · similarity 0.87)
- Viscosity Convergence Analysis for Deep Q-Networks (JMLR 2026 · similarity 0.87)
- SVQN: Sequential Variational Soft Q-Learning Networks (ICLR 2020 · similarity 0.87)
- Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning (NeurIPS 2025 · similarity 0.86)
- Stochastic Q-learning for Large Discrete Action Spaces (ICML 2024 · similarity 0.85)
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.
