Research map / Optimization / Nonconvex and smooth optimization
A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence
Carlo Alfano, Rui Yuan, Patrick Rebeschini
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 different omega-potential mirror maps (negative entropy, hyperbolic entropy, Euclidean, Tsallis with two entropic indices) in AMPO (ablation) | AMPO · CartPole and Acrobot | average return | Mixed |
| use negative entropy mirror map instead of other mirror maps in AMPO (ablation) | AMPO · CartPole and Acrobot | average return | Hurt |
| replace PPO with AMPO using various mirror maps and constant step-size 1 | PureJaxRL PPO · CartPole and Acrobot | average return | No clear effect |
Closest papers by meaning
- Learning mirror maps in policy mirror descent (ICLR 2025 · similarity 0.92)
- Policy Mirror Descent with Lookahead (NeurIPS 2024 · similarity 0.91)
- Operator World Models for Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- Convergence of Policy Mirror Descent Beyond Compatible Function Approximation (ICML 2025 · similarity 0.89)
- Sharp Convergence and Sample Complexity of Policy Mirror Descent for Average-Reward MDPs (NeurIPS 2026 · similarity 0.88)
- Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity (NeurIPS 2026 · similarity 0.88)
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.
