AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Improving Zero-Shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions

Bogdan Mazoure, Ilya Kostrikov, Ofir Nachum, Jonathan Tompson

NeurIPS 2022 · 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
Use reward-based GVF quantile similarity with GSF on CQLCQL · Offline Procgen, climberstandardized score: -0.263158 -> 1.894737Improved
Use reward-based GVF quantile similarity with GSF on CQLCQL · Offline Procgen, leaperstandardized score: 0.497143 -> -0.091429Hurt
Use action-count cumulants instead of reward or successor-feature cumulants (ablation)GSF · Offline Procgenzero-shot performanceMixed
Use categorical cross-entropy multiclass labels instead of pairwise InfoNCE (ablation)GSF · Offline Procgencontrastive loss errorImproved
Vary quantile-bin count K (ablation)GSF · Offline Procgenzero-shot performanceMixed
Vary softmax temperature tau (ablation)GSF · Offline Procgenzero-shot performanceMixed
Vary the structure of projection network h (ablation)GSF · Offline Procgenzero-shot performanceMixed

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