Research map / Optimization / Nonconvex and smooth optimization
Stochastic Variance Reduction Methods for Policy Evaluation
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 SVRG variance reduction instead of ordinary stochastic gradients | Policy evaluation on Random MDP and Mountain Car · Random MDP; Mountain Car | convergence speed | Helped |
| Use SAGA variance reduction instead of ordinary stochastic gradients | Policy evaluation on Random MDP and Mountain Car · Random MDP; Mountain Car | convergence speed | Helped |
| Increase regularization parameter ρ (ablation) | PDBG, SVRG, and SAGA · Random MDP | convergence speed | Helped |
| Increase regularization parameter ρ (ablation) | PDBG, SVRG, and SAGA · Mountain Car | convergence speed | Helped |
| Increase sample size n (ablation) | SVRG and SAGA · Mountain Car | convergence speed | Helped |
| Use SVRG or SAGA rather than GTD2 | Policy evaluation with a fixed dataset · EM-MSPBE policy evaluation | convergence rate | Helped |
| Rely on full-rank bilinear coupling rather than adding primal strong convexity | PDBG, SVRG, and SAGA · EM-MSPBE policy evaluation | convergence rate | Helped |
Closest papers by meaning
- Variance Reduced Policy Evaluation with Smooth Function Approximation (NeurIPS 2019 · similarity 0.92)
- Variance-Aware Off-Policy Evaluation with Linear Function Approximation (NeurIPS 2021 · similarity 0.90)
- Doubly Optimal Policy Evaluation for Reinforcement Learning (ICLR 2025 · similarity 0.90)
- On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method (NeurIPS 2021 · similarity 0.90)
- Policy Evaluation for Variance in Average Reward Reinforcement Learning (ICML 2024 · similarity 0.88)
- Efficient Multi-Policy Evaluation for Reinforcement Learning (AAAI 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.