AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Twice regularized MDPs and the equivalence between robustness and regularization

Esther Derman, Matthieu Geist, Shie Mannor

NeurIPS 2021 · Reinforcement learning › MDPs and planning · approach: Robust MDP policy gradient · 6 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 R² policy and value regularization instead of robust optimization updatesPolicy evaluation · 5×5 grid-worldcomputing time (sec.): 54.8 -> 0.02Improved
Use R² policy and value regularization instead of robust optimization updatesMPI, m=1 · 5×5 grid-worldcomputing time (sec.): 118.6 -> 0.03Improved
Use R² policy and value regularization instead of robust optimization updatesMPI, m=4 · 5×5 grid-worldcomputing time (sec.): 98.1 -> 0.03Improved
Add R² policy and value regularization to vanilla policy evaluationPolicy evaluation · 5×5 grid-worldcomputing time (sec.): 0.008 -> 0.02Hurt
Add R² policy and value regularization to vanilla MPIMPI, m=1 · 5×5 grid-worldcomputing time (sec.): 0.01 -> 0.03Hurt
Add R² policy and value regularization to vanilla MPIMPI, m=4 · 5×5 grid-worldcomputing time (sec.): 0.01 -> 0.03Hurt

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