Research map / Reinforcement learning / Policy gradient and actor-critic
Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds
Zhenghao Xu, Xiang Ji, Minshuo Chen, Mengdi Wang, Tuo Zhao
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 |
|---|---|---|---|
| increase image resolution from low to high (ambient dimension D x4) | NPMD · CartPole images, 8192 samples/iter | Max reward: 199.9 ± 0.1 -> 199.1 ± 0.9 | No clear effect |
| increase image resolution from high to super high | NPMD · CartPole images, 8192 samples/iter | Max reward: 199.1 ± 0.9 -> 196.7 ± 1.5 | Hurt |
| increase per-iteration sample size (2048, 4096, 8192) | NPMD · CartPole images | reward stability | Improved |
| increase total sample size | NPMD · CartPole images | average reward | Improved |
Closest papers by meaning
- Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces (ICLR 2025 · similarity 0.88)
- Learning mirror maps in policy mirror descent (ICLR 2025 · similarity 0.88)
- Policy Mirror Descent with Lookahead (NeurIPS 2024 · similarity 0.87)
- Convergence of Policy Mirror Descent Beyond Compatible Function Approximation (ICML 2025 · similarity 0.86)
- The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space (NeurIPS 2024 · similarity 0.86)
- Understanding and Diagnosing Deep Reinforcement Learning (ICML 2024 · similarity 0.86)
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.
