AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Dual Policy Iteration

Wen Sun, Geoffrey J. Gordon, Byron Boots, J. Bagnell

NeurIPS 2018 · Reinforcement learning › MDPs and planning · approach: POMDPs and confounded RL · 19 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use the intermediate expert's disadvantage Aη instead of the reactive policy's Aπ for policy updatesAggreVaTeD-VI · Random discrete MDPssample efficiencyImproved
Use local model-based search and expert disadvantage Aη for policy updates instead of TRPO-GAE's Aπ updateAggreVaTeD-iLQR · Continuous control taskssample efficiencyImproved
Use model-based expert guidance for policy updates instead of the model-free baselineAggreVaTeD-iLQR · Cart-Pole and Helicopter Funnel robust policy optimizationsample efficiencyImproved
Train on one environment instead of multiple training environments (ablation)AggreVaTeD-iLQR · Cart-Pole and Helicopter Funnel test environmentsconvergenceHurt
Add local model-based search to policy improvementDual Policy Iteration · Policy improvement per iterationpolicy improvementImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy