Research map / Reinforcement learning / Policy gradient and actor-critic
Operator Splitting Value Iteration
Amin Rakhsha, Andrew Wang, Mohammad Ghavamzadeh, Amir-massoud Farahmand
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 OS-VI instead of standard VI with an approximate model | control · 6x6 cliffwalk | normalized error of V^pi_k vs V* | Improved |
| use OS-Dyna instead of Q-Learning | RL · 6x6 cliffwalk | expected return V^pi_t(0) | Improved |
| use OS-Dyna instead of classic Dyna with model error | RL · 6x6 cliffwalk | expected return V^pi_t(0) | Improved |
| fully model-based planning with approximate model only | control · 6x6 cliffwalk | normalized error | Hurt |
Closest papers by meaning
- A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs (ICML 2025 · similarity 0.87)
- Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework (NeurIPS 2026 · similarity 0.86)
- A Unifying View of Linear Function Approximation in Off-Policy RL Through Matrix Splitting and Preconditioning (NeurIPS 2025 · similarity 0.86)
- Revisiting Value Iteration: Unified Analysis of Discounted and Average-Reward Cases (NeurIPS 2026 · similarity 0.85)
- Sketched Newton Value Iteration for Large-Scale Markov Decision Processes (AAAI 2024 · similarity 0.84)
- On the Second-Order Convergence of Biased Policy Gradient Algorithms (ICML 2024 · similarity 0.84)
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.
