Paper Citation Record · LEDGER

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies

As of 13 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2509.05735.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2509.05735 v1

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T05:09:29.269978Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

20 of 20 outbound references displayed

verified exact3
verified fuzzy5
unresolved10
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ee287cfc-e534-4381-acbc-8d2791ef3b3f · outbound

This paper cites Combating the Compounding-Error Problem with a Multi-step Model.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Combating the Compounding-Error Problem with a Multi-step Model

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T05:09:29.205646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32071725-ddd9-4c2f-b5c2-facf1b812fed · outbound

This paper cites Below, the training of the world model M includes training all components in Eq.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Below, the training of the world model M includes training all components in Eq

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:09:29.425275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 86bb3937-28c7-4ce8-90fb-f09a9540103e · outbound

This paper cites Regularized Behavior Value Estimation.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Regularized Behavior Value Estimation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T05:09:29.215472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 783a355f-10d1-4167-9e5b-b7b0dd5e819c · outbound

This paper cites A Survey on Offline Model-Based Reinforcement Learning.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies A Survey on Offline Model-Based Reinforcement Learning

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-08-05T05:09:29.343895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation aeccf0ce-10ea-4c16-809e-db11a1d5e6ce · outbound

This paper cites Discor: Corrective feedback in reinforcement learning via distribution correction.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Discor: Corrective feedback in reinforcement learning via distribution correction

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:09:29.454915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 49a3ba7d-8906-4510-b54e-b22e15165640 · outbound

This paper cites Andrew Bagnell.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Andrew Bagnell

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:09:29.445196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d18d4844-7d4d-422d-8037-d70e1072919e · outbound

This paper cites The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-05T05:09:29.324068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 372920bb-6144-4d2a-9de6-51c63bbeb966 · outbound

This paper cites Understanding the performance gap between online and offline alignment algorithms.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Understanding the performance gap between online and offline alignment algorithms

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T05:09:29.245182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea4bdc3f-4d47-4feb-b7de-06859784cd58 · outbound

This paper cites Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T05:09:29.248222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05cd2f78-30c3-45ae-a746-040560acf259 · outbound

This paper cites MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T05:09:29.251166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ba0897d-c032-412c-8d51-8790df24a9bc · outbound

This paper cites A Implementation Details A.1 Runtime Overview Our experiments comprised approximately 2000 runs, totaling 20000 GPU hours.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies A Implementation Details A.1 Runtime Overview Our experiments comprised approximately 2000 runs, totaling 20000 GPU hours

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:09:29.436594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ab6cea53-7737-43db-94cd-71264f022b31 · outbound

This paper cites -same”, while the different model initialization is marked with “-diff.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies -same”, while the different model initialization is marked with “-diff

Reference 19

Resolution: malformed identifier; raw_fallback, observed 2026-08-05T05:09:29.415889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a571720c-4a66-4583-aae5-55809fd18630 · outbound

This paper cites an unresolved cited work.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-05T05:09:29.406556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 45390c4c-59ae-464e-8f66-d06cee0d787c · outbound

This paper cites Mastering Diverse Domains through World Models.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Mastering Diverse Domains through World Models

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-05T05:09:29.222266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5422bfd4-e554-4c47-847b-13464b51c3e6 · outbound

This paper cites Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-05T05:09:29.228691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 970f977b-940e-4d93-b523-185692526cbc · outbound

This paper cites Exploring generalization and adaptability of offline reinforcement learning for robot manipulation.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Exploring generalization and adaptability of offline reinforcement learning for robot manipulation

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T05:09:29.464306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 912e2045-4ae9-4daa-b764-dd6721502493 · outbound

This paper cites Boosting Offline Reinforcement Learning via Data Rebalancing.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Boosting Offline Reinforcement Learning via Data Rebalancing

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-05T05:09:29.254979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e885a2ad-9441-46a0-af61-63eaf5aa4185 · outbound

This paper cites Learning Latent Dynamics for Planning from Pixels.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Learning Latent Dynamics for Planning from Pixels

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-05T05:09:29.219130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac127ea4-8e9e-4825-89da-61919d9a4b69 · outbound

This paper cites Knowledge Transfer from Teachers to Learners in Growing-Batch Reinforcement Learning.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Knowledge Transfer from Teachers to Learners in Growing-Batch Reinforcement Learning

Reference 2023

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T05:09:29.377909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a1289718-f32d-456a-b445-3dc26cc19514 · outbound

This paper cites Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL.

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL

Reference 2024

Resolution: verified exact; local_arxiv, observed 2026-08-05T05:09:29.389938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

No inbound Pith citation observations are available.