Research map / Learning theory and algorithms / Combinatorial and search optimization
Optimistic Planning by Regularized Dynamic Programming
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 |
|---|---|---|---|
| Add regularized policy and value updates to approximate value iteration | Optimistic planning in discounted MDPs · Discounted MDPs | expected regret | Helped |
| Use least-squares transition estimates with exploration bonuses in the regularized planning method | RAVI-UCB · Discounted linear mixture MDPs | expected regret: \widetilde{\calO} \sprt{ \sqrt{\sprt{d^2 H^3 + B^2 d H + H^4 \log \abs{\calA}} T}} | Helped |
| Use regularized dynamic programming rather than relying on contraction or monotonicity arguments | Optimistic planning with approximate Bellman operators · Discounted MDPs with function approximation | computational feasibility | Helped |
Closest papers by meaning
- Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs (NeurIPS 2026 · similarity 0.89)
- On the Convergence of Success Conditioning for Policy Optimization (NeurIPS 2026 · similarity 0.89)
- Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation (ICLR 2024 · similarity 0.88)
- Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity (ICML 2025 · similarity 0.88)
- Structure Matters: Dynamic Policy Gradient (NeurIPS 2025 · similarity 0.88)
- On the Complexity of Discounted Robust MDPs with $L_p$ Uncertainty Sets (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.