Research map / Reinforcement learning / MDPs and planning
Dual Policy Iteration
Wen Sun, Geoffrey J. Gordon, Byron Boots, J. Bagnell
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 the intermediate expert's disadvantage Aη instead of the reactive policy's Aπ for policy updates | AggreVaTeD-VI · Random discrete MDPs | sample efficiency | Improved |
| Use local model-based search and expert disadvantage Aη for policy updates instead of TRPO-GAE's Aπ update | AggreVaTeD-iLQR · Continuous control tasks | sample efficiency | Improved |
| Use model-based expert guidance for policy updates instead of the model-free baseline | AggreVaTeD-iLQR · Cart-Pole and Helicopter Funnel robust policy optimization | sample efficiency | Improved |
| Train on one environment instead of multiple training environments (ablation) | AggreVaTeD-iLQR · Cart-Pole and Helicopter Funnel test environments | convergence | Hurt |
| Add local model-based search to policy improvement | Dual Policy Iteration · Policy improvement per iteration | policy improvement | Improved |
Closest papers by meaning
- Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs (NeurIPS 2023 · similarity 0.89)
- Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework (NeurIPS 2026 · similarity 0.88)
- Diffusion Policy Policy Optimization (ICLR 2025 · similarity 0.88)
- Relative Policy-Transition Optimization for Fast Policy Transfer (AAAI 2024 · similarity 0.88)
- Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs (AAAI 2025 · similarity 0.88)
- A Unifying View of Linear Function Approximation in Off-Policy RL Through Matrix Splitting and Preconditioning (NeurIPS 2025 · similarity 0.87)
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.
