AI Paper Atlas

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

Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations

Yuping Luo, Tengyu Ma

NeurIPS 2021 · Reinforcement learning › Policy gradient and actor-critic · approach: Safety layers and shielding · 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
co-train barrier certificates, the dynamics model, and the policy, and explore only within certified statesCRABS · Upright, Tilt, Move, and Swingsafety violationsImproved
learn the barrier certificate rather than use a handcrafted certificate (ablation)CRABS · designed taskstotal rewardImproved
learn the barrier certificate rather than use a handcrafted certificate (ablation)CRABS · designed taskssafety violationsImproved
add regularization encouraging the certified region to include the previous epoch's region (ablation)CRABS barrier certificate · Movesize of certified viable subsetImproved
use SAC instead of CRABSCRABS · Move and Swingtotal rewardHurt

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