Paper Citation Record · LEDGER

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning

As of 7 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2604.20627.

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

pith.paper-citation-record.v1
2604.20627 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T00:19:48.053466Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

40 of 40 outbound references displayed

verified exact23
verified fuzzy10
unresolved5
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0e2ccc47-1dc8-44f4-bf9f-7eda98aeaa9c · outbound

This paper cites Option-aware temporally abstracted value for offline goal-conditioned reinforcement learning.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Option-aware temporally abstracted value for offline goal-conditioned reinforcement learning

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.170209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 630a03f4-edb0-4c48-ae11-d9505cb420a5 · outbound

This paper cites Full Shot Predictions for the DIII-D Tokamak via Deep Recurrent Networks.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Full Shot Predictions for the DIII-D Tokamak via Deep Recurrent Networks

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.167457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 721e048f-2b44-4b89-bbe9-2ad1e1b410c5 · outbound

This paper cites Temporal Difference Flows.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Temporal Difference Flows

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.158900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c66bfe18-9a1c-4107-a25b-10e7dd7c5f43 · outbound

This paper cites D4RL: Datasets for Deep Data-Driven Reinforcement Learning.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning D4RL: Datasets for Deep Data-Driven Reinforcement Learning

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-12T23:19:17.477461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 838fc5f5-88e3-4bcb-b5fd-9b32323775de · outbound

This paper cites Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.189847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8e04f272-435f-4266-9128-b8bbae6c1b1d · outbound

This paper cites Gaussian Error Linear Units (GELUs).

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Gaussian Error Linear Units (GELUs)

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.184872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5c2e4c50-ad5f-47de-83c6-2097faf5b1e8 · outbound

This paper cites Generative Temporal Difference Learning for Infinite-Horizon Prediction.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Generative Temporal Difference Learning for Infinite-Horizon Prediction

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.173297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b88afb4c-37a2-4c18-a19b-ddda345e0476 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Adam: A Method for Stochastic Optimization

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-10T00:24:47.182085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9697fd0e-9aa8-4ef5-8e08-8d09afd4f69f · outbound

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

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Offline Reinforcement Learning with Implicit Q-Learning

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:47:05.700994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 71b73c5c-1ee4-444b-8cca-8a06710a8f94 · outbound

This paper cites Automatic Reward Shaping from Confounded Offline Data.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Automatic Reward Shaping from Confounded Offline Data

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.192353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 93c2582f-c78e-4842-832f-deb3e4f6e6ff · outbound

This paper cites Flow Matching for Generative Modeling.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Flow Matching for Generative Modeling

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-10T00:24:47.194847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 721075b8-417a-4601-8da8-6fc2a3cbe5dd · outbound

This paper cites Flow Matching Guide and Code.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Flow Matching Guide and Code

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:28:14.320594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 56a29c79-bb3c-482c-925d-d536bda25bad · outbound

This paper cites Goal-Conditioned Reinforcement Learning: Problems and Solutions.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Goal-Conditioned Reinforcement Learning: Problems and Solutions

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.179747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3e597636-2626-49ea-8caf-c9ffcbacd396 · outbound

This paper cites Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.176236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3215fa87-042d-4aa9-8040-ebc2e2211928 · outbound

This paper cites Learning to Shape Rewards using a Game of Two Partners.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Learning to Shape Rewards using a Game of Two Partners

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.226301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 52b4f72d-a89e-4d2c-b643-2cc6aaad9b70 · outbound

This paper cites OGBench: Benchmarking Offline Goal-Conditioned RL.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning OGBench: Benchmarking Offline Goal-Conditioned RL

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.205459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7e2a2e4a-26d9-45ed-9d73-15404fe13326 · outbound

This paper cites Learning goal-conditioned policies from sub-optimal offline data via metric learning.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Learning goal-conditioned policies from sub-optimal offline data via metric learning

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.210600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 766122dd-1a85-40bc-a3d4-6c5163bbb1b5 · outbound

This paper cites Semi-parametric Topological Memory for Navigation.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Semi-parametric Topological Memory for Navigation

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.213063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1c069c93-9628-42a0-bf15-9fb229571ed1 · outbound

This paper cites Bellman diffusion models.arXiv preprint arXiv:2407.12163.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Bellman diffusion models.arXiv preprint arXiv:2407.12163

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.218256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 70989f6e-e878-4c1b-a5ec-6c1d25947041 · outbound

This paper cites Dual RL: Unification and New Methods for Reinforcement and Imitation Learning.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Dual RL: Unification and New Methods for Reinforcement and Imitation Learning

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T00:24:47.200049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 872eb0cf-fa4a-44df-b35d-076ed3bc29ea · outbound

This paper cites Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T00:24:47.220742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e53582ca-beba-4ed5-90ca-36d1efeb6910 · outbound

This paper cites Reward Models in Deep Reinforcement Learning: A Survey.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Reward Models in Deep Reinforcement Learning: A Survey

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.223690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fc2a4c6e-4f7f-453c-89cf-8aed4763308a · outbound

This paper cites Contrastive difference predictive coding.arXiv preprint arXiv:2310.20141, 2023a.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Contrastive difference predictive coding.arXiv preprint arXiv:2310.20141, 2023a

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.197432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 259cb14f-5fd5-4920-8c06-0f0295387358 · outbound

This paper cites Can a MISL fly? analysis and ingredients for mutual information skill learning.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Can a MISL fly? analysis and ingredients for mutual information skill learning

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.207972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 388c40ac-3e7e-437c-a9ee-6c140f4adc41 · outbound

This paper cites Flattening hierarchies with policy bootstrapping.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Flattening hierarchies with policy bootstrapping

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:24:47.202852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 270f7ae4-d91b-451c-8b1e-fc875d5e52d9 · outbound

This paper cites an unresolved cited work.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-05-23T11:27:55.427758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ef940040-5477-4b6f-abca-0042b9f320cc · outbound

This paper cites an unresolved cited work.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-05-23T11:27:55.420385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d2afbd84-a533-45aa-9292-360d046cdb1f · outbound

This paper cites an unresolved cited work.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-05-23T11:27:55.437349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cddef896-1a37-4cb8-9382-b8f9bd875b09 · outbound

This paper cites We start from the definition of squared Wasserstein-2 distance in Sec.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning We start from the definition of squared Wasserstein-2 distance in Sec

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:27:55.430729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bc841a1e-55db-4637-af32-a94ff0bfc09c · outbound

This paper cites an unresolved cited work.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-05-23T11:27:55.407343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 10c45c45-08f8-48a9-a921-269add10669e · outbound

This paper cites So we can lower bound the entire difference: V π∗ W (s1, g)−V π∗ W (s2, g)≥γ k−1 ·0 + k−2X t=0 γt(1−γ)∆ Φ = (1−γ)∆ Φ k−2X t=0 γt = (1−γ)∆ Φ 1−γ k−1 1−γ = (1−γ k−1)∆Φ.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning So we can lower bound the entire difference: V π∗ W (s1, g)−V π∗ W (s2, g)≥γ k−1 ·0 + k−2X t=0 γt(1−γ)∆ Φ = (1−γ)∆ Φ k−2X t=0 γt = (1−γ)∆ Φ 1−γ k−1 1−γ = (1−γ k−1)∆Φ

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:27:55.441151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b39f773b-00a8-4d0c-bad3-d5d2d382020d · outbound

This paper cites Both antmaze-large-navigateandantmaze-giant-navigateare collected with noisy expert SAC policies that repeatedly move towards randomly sampled goals (Park et al., 2024a).

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Both antmaze-large-navigateandantmaze-giant-navigateare collected with noisy expert SAC policies that repeatedly move towards randomly sampled goals (Park et al., 2024a)

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:27:55.434156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8873b6f1-c9e9-45a9-9ea9-661a625fb312 · outbound

This paper cites We use a dataset of raw sensor and actuator data collected from the DIII-D tokamak located in San Diego, CA, USA.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning We use a dataset of raw sensor and actuator data collected from the DIII-D tokamak located in San Diego, CA, USA

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:27:55.448423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f7cd042f-2e5f-4ce4-8c31-ff552912e6b6 · outbound

This paper cites Each RL algorithm was evaluated based on how closely it tracks a given goal state of the plasma.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Each RL algorithm was evaluated based on how closely it tracks a given goal state of the plasma

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:27:55.455107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4585f1b1-d50d-422e-9d83-e4cb18f56f39 · outbound

This paper cites an unresolved cited work.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-05-23T11:27:55.451431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3704338f-0131-4f86-8d8f-f08aed0d6565 · outbound

This paper cites We increased the R-Net size to an MLP of 64 units (we did not see an improvement in classification accuracy for large sizes) and used a local distance thresholdτ= 10 on all tasks.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning We increased the R-Net size to an MLP of 64 units (we did not see an improvement in classification accuracy for large sizes) and used a local distance thresholdτ= 10 on all tasks

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:27:55.424707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4cebef7f-36d7-44eb-8f69-eefa3872dd4f · outbound

This paper cites We provide the specific hyperparameters used for each task in Table.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning We provide the specific hyperparameters used for each task in Table

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:27:55.444953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 891ed8b7-99b1-4166-96c8-84111c2ecdb0 · outbound

This paper cites 3.2 and Sec.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning 3.2 and Sec

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:27:55.410453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4ac5fb54-4063-4c28-8a80-89f0be19e082 · outbound

This paper cites 4.1 for next next 1M epochs, however we did not see any consistent improvements from doing this.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning 4.1 for next next 1M epochs, however we did not see any consistent improvements from doing this

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:27:55.413770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e1b78d31-c015-4789-9914-acfa1db7bc03 · outbound

This paper cites For default GCIQL, policy training takes 7.2 ms per iteration.

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning For default GCIQL, policy training takes 7.2 ms per iteration

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T11:27:55.417304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

No inbound Pith citation observations are available.