Research map / Learning theory and algorithms / Sample complexity
A new convergent variant of Q-learning with linear function approximation
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 coupled two-time-scale update (CQL) instead of standard Q-learning | linear Q-learning · theta->2theta example | Q-value norm convergence | Helped |
| use CQL instead of standard Q-learning | linear Q-learning · star counterexample | Q-value convergence | Helped |
| use CQL instead of GGQ | GGQ · star counterexample | convergence to true solution | Helped |
| use CQL instead of Q-learning (l=2, eta=1) | Q-learning · Mountain car | average cumulative reward: -167.98 ± 39.22 -> -148.99 ± 36.33 | Helped |
| use CQL instead of Q-learning (l=8, eta=0.25) | Q-learning · Mountain car | average cumulative reward: -121.43 ± 14.50 -> -144.94 ± 33.76 | Hurt |
| use CQL vs baselines across mountain car architectures | Q-learning/GGQ · Mountain car | average cumulative reward | Mixed |
Closest papers by meaning
- Regularized Q-Learning (NeurIPS 2024 · similarity 0.91)
- Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set (ICML 2025 · similarity 0.90)
- A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation (NeurIPS 2024 · similarity 0.89)
- Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities (NeurIPS 2026 · similarity 0.89)
- A Unifying View of Linear Function Approximation in Off-Policy RL Through Matrix Splitting and Preconditioning (NeurIPS 2025 · similarity 0.88)
- Stochastic Q-learning for Large Discrete Action Spaces (ICML 2024 · 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.