Research map / Reinforcement learning / MDPs and planning
A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes
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 |
|---|---|---|---|
| optimistic PPO with multi-batched updating in linear MDPs | OPPO+ · stochastic linear MDPs, bandit feedback | regret bound: H^{13/4} -> H^2 | Helped |
| policy-based OPPO+ versus prior policy-based method with 8/9 exponent | OPPO+ · adversarial linear MDPs, full information | regret exponent in K: K^{8/9} -> K^{3/4} | Helped |
| OPPO+ versus K^{6/7} prior work | OPPO+ · adversarial linear MDPs, full information | regret exponent in K: K^{6/7} -> K^{3/4} | Helped |
Closest papers by meaning
- Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.90)
- Rate-Optimal Policy Optimization for Linear Markov Decision Processes (ICML 2024 · similarity 0.89)
- Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation (NeurIPS 2025 · similarity 0.89)
- Achieving Constant Regret in Linear Markov Decision Processes (NeurIPS 2024 · similarity 0.89)
- Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback (ICLR 2024 · similarity 0.89)
- PPO in the Fisher-Rao geometry (NeurIPS 2026 · similarity 0.89)
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.