AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Safe Policy Optimization with Local Generalized Linear Function Approximations

Akifumi Wachi, Yunyue Wei, Yanan Sui

NeurIPS 2021 · Reinforcement learning › Policy gradient and actor-critic · approach: Safety layers and shielding · 2 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 SPO-LF with local features and safety-constrained policy optimizationGym-MiniGrid 25×25 · Gym-MiniGrid 25×25unsafe actions: 0.0 vs 3.4 for Unsafe GLM and 49.0 for RandomImproved
Use SPO-LF with local features and safety-constrained policy optimizationSafety-Gym · Safety-Gymunsafe actions: 0Improved
Add far-sighted observations by increasing field of view (ablation)SPO-LF · Gym-MiniGridconvergence speedImproved
Remove event-triggered safe expansion (ETSE) (ablation)SPO-LF · Gym-MiniGridrewardHurt
Use SPO-LF instead of CPO, PPO-Lagrangian, or TRPO-LagrangianSafety-Gym · Safety-GymrewardNo clear effect

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