AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples

Hao Sun, Alihan Hüyük, Daniel Jarrett, Mihaela van der Schaar

NeurIPS 2023 · Reinforcement learning › Offline RL · approach: Simple practical offline RL · 0 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
Increase the epsilon quantile from 0.5 to 0.9, filtering fewer candidate actions (ablation)AOC · Pendulum-Hetperformance: -1.25 ± 0.40 -> -503.39 ± 301.60Hurt
Increase the epsilon quantile from 0.5 to 1.0, filtering fewer candidate actions (ablation)AOC · Pendulum-Hetperformance: -1.25 ± 0.40 -> -853.29 ± 138.43Hurt
Decrease the epsilon quantile from 0.5 to 0.3 (ablation)AOC · Pendulum-Hetperformance: -1.25 ± 0.40 -> -2.05 ± 0.45Hurt
Use the corpus-residual filter to exclude actions with larger residuals (ablation)AOC · Pendulum-Hetcumulative reward: -853.29 ± 138.43 -> -1.25 ± 0.40Improved
Increase the proportion of offline trajectories from expert π1AOC · Continuous Mazeupper-gate route selectionImproved
Adjust the proportion of reference behaviors through re-sampling or sub-samplingAOC · Continuous Mazesuccess rateNo clear effect
Increase the offline dataset sizeMFRL · Pendulum-Hetcumulative reward: -4.1 ± 2.76 -> -15.27 ± 6.46Hurt

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