Research map / Optimization / Optimizers
A Kernel Loss for Solving the Bellman Equation
Yihao Feng, Lihong Li, Qiang Liu
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 |
|---|---|---|---|
| Use K-loss instead of FVI or TD(0) | Value-function learning · Modified stochastic 5-state example | value-function error | Improved |
| Use K-loss instead of residual gradient | Value-function learning · Modified stochastic 5-state example | value-function error | Improved |
| Use K-loss instead of residual gradient | Neural-network policy evaluation · Puddle World | MSE | Improved |
| Use K-loss instead of FVI or TD(0) | Neural-network policy evaluation · Puddle World | stability | Improved |
| Use K-loss instead of other evaluated value-learning methods | Neural-network policy evaluation · CartPole and Mountain Car | value-function learning performance | Improved |
| Replace the Trust-PCL critic update with K-loss | Trust-PCL · Mujoco benchmark | policy performance | Improved |
| Use V-statistics instead of U-statistics (ablation) | K-loss estimation · Policy evaluation and policy optimization experiments | learning performance | Improved |
Closest papers by meaning
- Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework (NeurIPS 2026 · similarity 0.88)
- Parameterized Projected Bellman Operator (AAAI 2024 · similarity 0.88)
- Inverting the Bellman Equation: From $Q$-Values to World Models (NeurIPS 2026 · similarity 0.88)
- Enhancing Value Function Estimation through First-Order State-Action Dynamics in Offline Reinforcement Learning (ICML 2024 · similarity 0.88)
- Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics (ICLR 2025 · similarity 0.87)
- Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning (ICML 2025 · similarity 0.87)
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.
