Paper Citation Record · LEDGER

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations

As of 15 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2505.21182.

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

pith.paper-citation-record.v1
2505.21182 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:45:23.355646Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

44 of 44 outbound references displayed

verified exact0
verified fuzzy23
unresolved20
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2c4628ce-86d1-4cff-8765-84ec7d88f045 · outbound

This paper cites Learning from negative feedback, or positive feedback or both.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Learning from negative feedback, or positive feedback or both

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:27.082515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 64791b30-10ef-4627-999a-145bda6aa78a · outbound

This paper cites Ls-iq: Implicit reward regularization for inverse reinforcement learning.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Ls-iq: Implicit reward regularization for inverse reinforcement learning

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:26.925023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 205dd793-60b9-4425-8f25-4bd24ed16200 · outbound

This paper cites Non-Adversarial Imitation Learning and its Connections to Adversarial Methods.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Non-Adversarial Imitation Learning and its Connections to Adversarial Methods

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:20.621562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1912d9ba-2283-44e0-a095-7e5dfd3e11fa · outbound

This paper cites Extrapolating beyond sub- optimal demonstrations via inverse reinforcement learning from observations.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Extrapolating beyond sub- optimal demonstrations via inverse reinforcement learning from observations

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:26.765071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2ff03470-5320-4fbd-8bb1-bfeb0b9a8d81 · outbound

This paper cites Diffusion policy: Visuomotor policy learning via action diffusion.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Diffusion policy: Visuomotor policy learning via action diffusion

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:20.779872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f2ea788-3d62-438b-88ee-8c8cc41ed391 · outbound

This paper cites D4rl: Datasets for deep data-driven reinforcement learning, 2020.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations D4rl: Datasets for deep data-driven reinforcement learning, 2020

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:20.857897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f188ec89-2133-4a54-a83c-56d677b9d520 · outbound

This paper cites Learning robust rewards with adverserial inverse reinforcement learning.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Learning robust rewards with adverserial inverse reinforcement learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:20.920843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86f6ff67-01e4-47cf-b0ed-66feb0e9666e · outbound

This paper cites Iq-learn: Inverse soft-q learning for imitation.Advances in Neural Information Processing Systems, 34:4028–4039, 2021.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Iq-learn: Inverse soft-q learning for imitation.Advances in Neural Information Processing Systems, 34:4028–4039, 2021

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:26.595388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d41efe19-f51f-4820-8ae0-df59e29f62bb · outbound

This paper cites Extreme q-learning: Maxent rl without entropy.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Extreme q-learning: Maxent rl without entropy

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:21.055628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1348ed5c-b626-47c2-ab7a-4e0dd31a737d · outbound

This paper cites Offline safe reinforcement learning using trajectory classification.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Offline safe reinforcement learning using trajectory classification

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:21.109441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e858749-43b9-4743-87e9-9156840f9d29 · outbound

This paper cites Generative adversarial nets.Advances in neural information processing systems, 27, 2014.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Generative adversarial nets.Advances in neural information processing systems, 27, 2014

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:21.208925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac492e48-001b-49a3-84c5-adc1112e90ac · outbound

This paper cites Soft Actor-Critic Algorithms and Applications.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Soft Actor-Critic Algorithms and Applications

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:21.257006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f529ed5b-29a9-4cd9-8198-801404ef02b1 · outbound

This paper cites Inverse preference learning: Preference-based rl without a reward function.Advances in Neural Information Processing Systems, 36, 2024.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Inverse preference learning: Preference-based rl without a reward function.Advances in Neural Information Processing Systems, 36, 2024

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:26.457263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 52247b9e-19c1-4021-b86a-6b26c97c4c89 · outbound

This paper cites Generative adversarial imitation learning.Advances in neural information processing systems, 29, 2016.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Generative adversarial imitation learning.Advances in neural information processing systems, 29, 2016

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:21.394551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d50e597-f61d-4d14-9411-548562ffd556 · outbound

This paper cites Imitate the good and avoid the bad: An incremental approach to safe reinforcement learning.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Imitate the good and avoid the bad: An incremental approach to safe reinforcement learning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:26.322307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 18031182-88ee-4a67-8ca0-f491a21621ec · outbound

This paper cites SPRINQL: Sub-optimal demonstrations driven offline imitation learning.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations SPRINQL: Sub-optimal demonstrations driven offline imitation learning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:26.199634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 901b9955-899b-4905-bd1f-374821406b14 · outbound

This paper cites Safedice: offline safe imitation learning with non-preferred demonstra- tions.Advances in Neural Information Processing Systems, 36, 2024.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Safedice: offline safe imitation learning with non-preferred demonstra- tions.Advances in Neural Information Processing Systems, 36, 2024

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:26.034700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ebccd9e9-1a93-44c6-9eab-f3f86727b428 · outbound

This paper cites Beyond reward: Offline preference-guided policy optimization.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Beyond reward: Offline preference-guided policy optimization

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:25.922860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7555e766-7186-488c-8900-13cc48bdb504 · outbound

This paper cites Preference transformer: Modeling human preferences using transformers for rl.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Preference transformer: Modeling human preferences using transformers for rl

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:25.802081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8c6f081a-5732-4def-a972-acfccd6b7c0e · outbound

This paper cites Lobs- dice: Offline learning from observation via stationary distribution correction estimation.Ad- vances in Neural Information Processing Systems, 35:8252–8264, 2022.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Lobs- dice: Offline learning from observation via stationary distribution correction estimation.Ad- vances in Neural Information Processing Systems, 35:8252–8264, 2022

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:25.682139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 929132a5-0aa2-4164-98bd-73051ca1f061 · outbound

This paper cites Demodice: Offline imitation learning with supplementary imperfect demonstrations.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Demodice: Offline imitation learning with supplementary imperfect demonstrations

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:25.533048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bfa6dfa9-835d-4cee-bdb3-be81a1ea7a78 · outbound

This paper cites Imitation learning via off-policy distribu- tion matching.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Imitation learning via off-policy distribu- tion matching

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:25.377199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d7cd0d06-b351-4edb-9629-fd5a4efa2c3e · outbound

This paper cites Offline Reinforcement Learning with Implicit Q-Learning.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Offline Reinforcement Learning with Implicit Q-Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:22.055691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c410392f-0d3c-49c1-8657-0c1196d72813 · outbound

This paper cites Optidice: Offline policy optimization via stationary distribution correction estimation.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Optidice: Offline policy optimization via stationary distribution correction estimation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:22.126583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04ffb083-fa8c-4686-9284-074cbef611d2 · outbound

This paper cites Imitation learning from imperfection: Theoretical justifications and algorithms.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Imitation learning from imperfection: Theoretical justifications and algorithms

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:25.226569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4300174b-ee62-44f9-b5f0-eda6a886c6ce · outbound

This paper cites Semantic loss guided data efficient supervised fine tuning for safe responses in LLMs.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Semantic loss guided data efficient supervised fine tuning for safe responses in LLMs

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:25.070431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 424ddd85-30e7-4b83-a606-3b869189a8f4 · outbound

This paper cites Versatile offline imitation from observations and examples via regularized state-occupancy matching.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Versatile offline imitation from observations and examples via regularized state-occupancy matching

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:24.903313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fc3ca09a-e016-4aee-864b-8f1883a7923c · outbound

This paper cites ODICE: Revealing the mystery of distribution correction estimation via orthogonal-gradient update.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations ODICE: Revealing the mystery of distribution correction estimation via orthogonal-gradient update

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:24.765969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 30e0c133-e747-4e70-b5df-da0660b6d98f · outbound

This paper cites Human-level control through deep reinforcement learning.nature, 518(7540):529–533, 2015.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Human-level control through deep reinforcement learning.nature, 518(7540):529–533, 2015

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:22.428158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cee96929-d64e-44c2-92d4-d7c3dda9849d · outbound

This paper cites Learning multimodal rewards from rankings.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Learning multimodal rewards from rankings

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:24.635468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8c0e79a4-3bab-4f99-8b9d-9ac36a579a56 · outbound

This paper cites AlgaeDICE: Policy Gradient from Arbitrary Experience.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations AlgaeDICE: Policy Gradient from Arbitrary Experience

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:22.530387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff04da8a-4818-467b-9f2a-93a3d7b4b752 · outbound

This paper cites John Wiley & Sons, 2014.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations John Wiley & Sons, 2014

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:22.584986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adfc0d2e-f24c-41f9-a220-8b6384514e8b · outbound

This paper cites SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:22.644916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c709bc1-4fb8-4153-815e-febcac13d146 · outbound

This paper cites A reduction of imitation learning and structured prediction to no-regret online learning.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations A reduction of imitation learning and structured prediction to no-regret online learning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:22.713611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1baaf247-61f6-47a5-ae5f-0ac77832350a · outbound

This paper cites Dual rl: Unification and new methods for reinforcement and imitation learning.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Dual rl: Unification and new methods for reinforcement and imitation learning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:24.463802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 60918259-124d-4b73-b803-98d1a04efbdd · outbound

This paper cites Value-Decomposition Networks For Cooperative Multi-Agent Learning.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Value-Decomposition Networks For Cooperative Multi-Agent Learning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:22.895040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c1093c0-bad7-441b-9fa6-b7006eeb0969 · outbound

This paper cites Sutton and Andrew G.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Sutton and Andrew G

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:22.948033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6e1ccb1-e0e2-4803-9c4d-9ca5b907b114 · outbound

This paper cites Behavioral Cloning from Observation.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Behavioral Cloning from Observation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:23.005235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a076efa-b485-4645-923a-c19e040ddb10 · outbound

This paper cites Imitation learning from imperfect demonstration.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Imitation learning from imperfect demonstration

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:24.346386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation df5684c9-6a3e-42b4-8da1-9a4b96a64f1c · outbound

This paper cites Discriminator-weighted offline imitation learning from suboptimal demonstrations.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Discriminator-weighted offline imitation learning from suboptimal demonstrations

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:24.184828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4b9daa03-61a6-495c-9682-1b5c4454e25c · outbound

This paper cites How to leverage diverse demonstrations in offline imitation learning.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations How to leverage diverse demonstrations in offline imitation learning

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:24.054467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e736db86-5661-4b4c-b36d-6f2ba6a1e9fb · outbound

This paper cites Confidence-aware imitation learning from demonstrations with varying optimality.Advances in Neural Information Pro- cessing Systems, 34:12340–12350, 2021.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Confidence-aware imitation learning from demonstrations with varying optimality.Advances in Neural Information Pro- cessing Systems, 34:12340–12350, 2021

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:45:23.927034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 79f27f97-9f66-46a0-95b4-3fc3ab98fc96 · outbound

This paper cites Learning fine-grained bimanual manipulation with low-cost hardware.Robotics: Science and Systems XIX, 2023.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations Learning fine-grained bimanual manipulation with low-cost hardware.Robotics: Science and Systems XIX, 2023

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T13:45:23.301455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bc48ea3-2bd1-4766-9042-4b38461a3eaf · outbound

This paper cites The ingredients of real world robotic reinforcement learning.

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations The ingredients of real world robotic reinforcement learning

Reference 44

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T13:45:23.733063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.