Research map / Reinforcement learning / MDPs and planning
Efficiently Solving MDPs with Stochastic Mirror Descent
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 primal-dual stochastic mirror descent without the prior method's additional ergodicity condition | Mixing AMDPs · Mixing AMDP | sample complexity: \Otilb{\tau^2\tmix^2\A\eps^{-2}} -> \Otilb{\tmix^2\A\eps^{-2}} | Helped |
| Use primal-dual stochastic mirror descent | Discounted MDPs · Discounted MDP | sample complexity: \Otilb{(1-\gamma)^{-4}\A\eps^{-2}} vs. \Otilb{(1-\gamma)^{-3}\A\eps^{-2}} | Mixed |
| Use local-norm variance bounds and carefully designed stochastic gradient estimators | Box-simplex bilinear saddle-point problems · \ell_\infty-\ell_1 bilinear games | runtime: \Otilde{((m+n)\linf{\M}^2+n\lones{\bb}^2+m\linf{\cc}^2)\eps^{-2}} | Helped |
Closest papers by meaning
- Sharp Convergence and Sample Complexity of Policy Mirror Descent for Average-Reward MDPs (NeurIPS 2026 · similarity 0.93)
- Policy Mirror Descent with Lookahead (NeurIPS 2024 · similarity 0.90)
- Mirror descent actor-critic methods for entropy regularised MDPs in general spaces: stability and convergence (NeurIPS 2026 · similarity 0.88)
- Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm (NeurIPS 2025 · similarity 0.88)
- Policy Optimization for Robust Average Reward MDPs (NeurIPS 2024 · similarity 0.88)
- Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm (NeurIPS 2024 · 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.