Research map / Optimization / Optimizers
Viscosity Convergence Analysis for Deep Q-Networks
Qian Qi
Read the paperCheck your idea against 137,217 papers
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 monotone non-negative spatial coupling (vs pointwise PINN) | neural HJB solver · 1D saturated LQR | monotonicity violations (%): 59.95 -> 0.00 | Improved |
| add monotone non-negative spatial coupling (vs pointwise PINN) | neural HJB solver · 1D saturated LQR | max overshoot at kink: 6.03 × 10^6 -> 6.02 × 10^-2 | Improved |
| add monotone spatially-coupled stencil (vs pointwise PINN) | neural HJB solver · 2D stochastic navigation | global MSE: 325.25217 -> 0.96973 | Improved |
| replace ReLU with Tanh activation (ablation) | Monotone ResNet · 1D saturated LQR | final MSE: 73.773 -> 74.328 | No clear effect |
| train longer (1,000 to 30,000 iterations) | Monotone ResNet · 1D LQR consistency test bank | overall delta_max: 6.738 -> 6.573 | Improved |
Closest papers by meaning
- Universal Approximation Theorem of Deep Q-Networks (ICML 2025 · similarity 0.90)
- Convergent and Efficient Deep Q Learning Algorithm (ICLR 2022 · similarity 0.88)
- Weakly Coupled Deep Q-Networks (NeurIPS 2023 · similarity 0.87)
- Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning (NeurIPS 2025 · similarity 0.84)
- Stochastic Q-learning for Large Discrete Action Spaces (ICML 2024 · similarity 0.84)
- Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning (ICLR 2025 · similarity 0.84)
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.
