AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning

Dingwen Kong, Lin Yang

NeurIPS 2022 · Reinforcement learning › MDPs and planning · approach: Policy optimization theory · 1 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
choose reward queries actively instead of uniformly sampling from the exploration dataset (ablation)reward-free exploration plus reward learning algorithm · random two-stage tabular MDP (S=20, A=10/3), noise margin 0.05queries needed for target policy accuracyImproved
vary the noise margin Delta with N=100 queries fixedactive reward learning algorithm · random two-stage tabular MDP, d=5, K=2000policy error V1*(s1) - V1(s1)Mixed
compare active vs passive learning across noise margins (ablation)active reward learning algorithm · random two-stage tabular MDP, N=100 queriespolicy errorImproved

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