AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability

Hanlin Zhu, Amy Zhang

NeurIPS 2023 · Reinforcement learning › Offline RL · approach: Offline-to-online fine-tuning · 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
Tune α from 1 to 0.5 (ablation)VP-learning / GoFAR · FetchReachdiscounted return: 27.3 ± 0.34 -> 27.5 ± 0.29No clear effect
Tune α from 1 to 0.2 (ablation)VP-learning / GoFAR · FetchPickdiscounted return: 18.2 ± 1.2 -> 20.7 ± 0.9Improved
Tune α from 1 to 0.1 (ablation)VP-learning / GoFAR · FetchPushdiscounted return: 19.6 ± 1.6 -> 20.3 ± 2.5Improved
Tune α from 1 to 0.5 (ablation)VP-learning / GoFAR · FetchSlidediscounted return: 2.75 ± 1.84 -> 3.47 ± 1.08Mixed
Tune α from 1 to 0.05 (ablation)VP-learning / GoFAR · HandReachdiscounted return: 7.13 ± 3.60 -> 8.98 ± 3.11Mixed
Use α=0.1 instead of α=1 (ablation)VP-learning / GoFAR · FetchPushfinal distance: 0.043 ± 0.012 -> 0.027 ± 0.002Improved
Use α=0.2 instead of α=1 (ablation)VP-learning / GoFAR · FetchPickfinal distance: 0.043 ± 0.011 -> 0.031 ± 0.004Improved
Use α=0.5 instead of α=1 (ablation)VP-learning / GoFAR · FetchSlidefinal distance: 0.1202 ± 0.019 -> 0.1017 ± 0.017Improved
Use α=0.5 instead of α=1 (ablation)VP-learning / GoFAR · HandReachfinal distance: 0.026828 ± 0.0044 -> 0.026826 ± 0.0049No clear effect
Use α=2 instead of α=1 (ablation)VP-learning / GoFAR · FetchSlidediscounted return: 2.75 ± 1.84 -> 1.80 ± 0.66Hurt
Use α=0.2 instead of α=1 (ablation)VP-learning / GoFAR · HandReachdiscounted return: 7.13 ± 3.60 -> 2.92 ± 0.98Hurt

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