AI Paper Atlas

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

Neurosymbolic Reinforcement Learning with Formally Verified Exploration

Greg Anderson, Abhinav Verma, Isil Dillig, Swarat Chaudhuri

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Safety layers and shielding · 14 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
update the shield during learning instead of keeping a static shield (ablation)REVEL · 10 continuous-control benchmarkstraining cost: better on 4 of 10 benchmarks, very substantial on noisy-road and mountain-carImproved
use REVEL's neurosymbolic verified policy instead of DDPGREVEL · 10 continuous-control benchmarkspolicy cost: competitive or better on 7 of 10; slightly worse on 2; much better on car-racingMixed
use REVEL instead of CPOREVEL · 10 continuous-control benchmarkspolicy cost: better on 4 of 10, slightly worse on 2Mixed
enforce verified shielding (REVEL) vs unverified DDPG/CPOREVEL · 10 benchmarkssafety violations during training: DDPG and CPO violate safety in 8 of 10 benchmarks, e.g. CPO 9906 on pendulumImproved
repeated shield synthesis inside the learning loopREVEL · 10 benchmarkstraining time: 87% of time in shield synthesis on average; 95.1% on road-2dHurt

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