Paper Citation Record · LEDGER

Self-Composing Policies for Scalable Continual Reinforcement Learning

As of 14 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 2 inbound Pith citation observations for arXiv:2506.14811.

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

pith.paper-citation-record.v1
2506.14811 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:55:39.186629Z

measured 46 of 46 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T22:43:20.198877Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T20:58:57.542814Z

Reference resolution

44 of 44 outbound references displayed

verified exact0
verified fuzzy30
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4be8b203-e0fb-4c71-8697-77f2f8a2ce5d · outbound

This paper cites P., Piot, B., Kapturowski, S., Sprechmann, P., Vitvitskyi, A., Guo, Z.

Self-Composing Policies for Scalable Continual Reinforcement Learning P., Piot, B., Kapturowski, S., Sprechmann, P., Vitvitskyi, A., Guo, Z

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.844779Z

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 29d1ae43-8179-4f64-84fb-f5ad099f7a0e · outbound

This paper cites Therefore, the computational cost of the internal policy is constant and independent of the number of modules (i.e., number of tasks), Tint(n) = O(1).9 Total Complexity.

Self-Composing Policies for Scalable Continual Reinforcement Learning Therefore, the computational cost of the internal policy is constant and independent of the number of modules (i.e., number of tasks), Tint(n) = O(1).9 Total Complexity

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.530805Z

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 21cc310c-e4f7-4b09-a6c0-1410f23e4681 · outbound

This paper cites 9For the sake of simplicity, this definition of the internal policy ignores possible activation and normalization layers.

Self-Composing Policies for Scalable Continual Reinforcement Learning 9For the sake of simplicity, this definition of the internal policy ignores possible activation and normalization layers

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.518424Z

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 7d9e6bba-2c93-477c-9eaf-78918cfc303b · outbound

This paper cites an unresolved cited work.

Self-Composing Policies for Scalable Continual Reinforcement Learning Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:55:39.318128Z

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 43f60adf-e129-40b9-b512-02b32f0f0990 · outbound

This paper cites an unresolved cited work.

Self-Composing Policies for Scalable Continual Reinforcement Learning Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:55:39.478802Z

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 92e3bb62-861f-408c-b619-21bf06002c47 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Self-Composing Policies for Scalable Continual Reinforcement Learning An image is worth 16x16 words: Transformers for image recognition at scale

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.788091Z

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 f5af5f3d-0b1a-4818-a396-6ef6ff47680b · outbound

This paper cites Finally, note that the diagonal of the matrix has no especially positive transfer values.

Self-Composing Policies for Scalable Continual Reinforcement Learning Finally, note that the diagonal of the matrix has no especially positive transfer values

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.429837Z

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 317d1efb-d88a-4b17-a8bc-4acfd852c627 · outbound

This paper cites DARLA: Improving zero-shot transfer in reinforcement learning.

Self-Composing Policies for Scalable Continual Reinforcement Learning DARLA: Improving zero-shot transfer in reinforcement learning

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.742282Z

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 34695499-3440-48c5-af70-84f4bfedb10b · outbound

This paper cites A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al.

Self-Composing Policies for Scalable Continual Reinforcement Learning A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.718636Z

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 1d659b91-6234-4ad0-a7b6-199a0bf6b0c5 · outbound

This paper cites and Lazebnik, S.

Self-Composing Policies for Scalable Continual Reinforcement Learning and Lazebnik, S

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.694872Z

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 b1880b98-c986-479a-807b-d8a5e7f7e7b4 · outbound

This paper cites and Cohen, N.

Self-Composing Policies for Scalable Continual Reinforcement Learning and Cohen, N

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.683418Z

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 667d9567-5c7f-4e7d-99c0-c3f727a7ed7b · outbound

This paper cites A., van Seijen, H., and EATON, E.

Self-Composing Policies for Scalable Continual Reinforcement Learning A., van Seijen, H., and EATON, E

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.671874Z

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 abf8d190-968e-4e5e-bdc5-332a66797733 · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

Self-Composing Policies for Scalable Continual Reinforcement Learning DINOv2: Learning Robust Visual Features without Supervision

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:39.090901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b373c6e9-68e2-495b-9dca-23d67dc39192 · outbound

This paper cites Routing net- works: Adaptive selection of non-linear functions for multi-task learning.

Self-Composing Policies for Scalable Continual Reinforcement Learning Routing net- works: Adaptive selection of non-linear functions for multi-task learning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.660530Z

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 cfa1ce0d-f908-4a27-975a-5f9289193564 · outbound

This paper cites Routing Networks and the Challenges of Modular and Compositional Computation.

Self-Composing Policies for Scalable Continual Reinforcement Learning Routing Networks and the Challenges of Modular and Compositional Computation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:39.098469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0746266a-c85f-4f8b-9142-dda724f93ded · outbound

This paper cites Policy Distillation.

Self-Composing Policies for Scalable Continual Reinforcement Learning Policy Distillation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:39.102242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da3f200e-103e-4462-a5b4-ac87ac9a71cb · outbound

This paper cites Proximal Policy Optimization Algorithms.

Self-Composing Policies for Scalable Continual Reinforcement Learning Proximal Policy Optimization Algorithms

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:39.113642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7818e6b-4ab2-4712-af14-45ad343e455b · outbound

This paper cites V ., Montone, G., and O’Regan, J.

Self-Composing Policies for Scalable Continual Reinforcement Learning V ., Montone, G., and O’Regan, J

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.636813Z

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 0d88f8cf-b4f8-4749-b2d1-37c7a231577c · outbound

This paper cites Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions.

Self-Composing Policies for Scalable Continual Reinforcement Learning Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:39.124267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b2bef20-85a1-4998-9847-c983e7a125c1 · outbound

This paper cites Continual World: A robotic benchmark for continual reinforcement learning.

Self-Composing Policies for Scalable Continual Reinforcement Learning Continual World: A robotic benchmark for continual reinforcement learning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.613338Z

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 db873ac4-15e5-46c8-b2ee-299fc137e60c · outbound

This paper cites Disentangling transfer in continual reinforce- ment learning.

Self-Composing Policies for Scalable Continual Reinforcement Learning Disentangling transfer in continual reinforce- ment learning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.600999Z

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 0be4bb6a-e033-4289-8d30-9dfa8b22ba9c · outbound

This paper cites Supermasks in superposition.

Self-Composing Policies for Scalable Continual Reinforcement Learning Supermasks in superposition

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.589259Z

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 36588c15-1180-4e78-8b3f-0c2f3a36d725 · outbound

This paper cites Smoothquant: Accurate and efficient post-training quantization for large language models.

Self-Composing Policies for Scalable Continual Reinforcement Learning Smoothquant: Accurate and efficient post-training quantization for large language models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.577244Z

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 15547404-9f2a-4fe1-ad86-8cce9832ae89 · outbound

This paper cites an unresolved cited work.

Self-Composing Policies for Scalable Continual Reinforcement Learning Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:55:39.565574Z

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 869064b6-bead-4ec4-9e81-efe63dee22ae · outbound

This paper cites Gradient surgery for multi-task learning.

Self-Composing Policies for Scalable Continual Reinforcement Learning Gradient surgery for multi-task learning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.554336Z

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 6c868104-f8c8-4cbd-b35c-f38e7c2a5702 · outbound

This paper cites an unresolved cited work.

Self-Composing Policies for Scalable Continual Reinforcement Learning Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:55:39.542556Z

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 cdbc379b-2fa6-4fc8-8f39-c6290181e1db · outbound

This paper cites an unresolved cited work.

Self-Composing Policies for Scalable Continual Reinforcement Learning Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:55:39.506391Z

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 0345a13f-de38-45e8-b284-cea6ba45f785 · outbound

This paper cites Trucks are longer vehicles, and thus, more difficult to avoid.

Self-Composing Policies for Scalable Continual Reinforcement Learning Trucks are longer vehicles, and thus, more difficult to avoid

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.494181Z

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 0b094072-7127-4a85-94a4-20fc1d88beb7 · outbound

This paper cites Figure D.2c provides the FTr matrix of the last sequence, Freeway.

Self-Composing Policies for Scalable Continual Reinforcement Learning Figure D.2c provides the FTr matrix of the last sequence, Freeway

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.378668Z

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 08374901-c3a0-459e-865a-8deda8b0d0ee · outbound

This paper cites All methods share the same common hyperparameters in every task sequence.

Self-Composing Policies for Scalable Continual Reinforcement Learning All methods share the same common hyperparameters in every task sequence

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.347211Z

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 e28708de-c8ff-486f-8755-3ffb3c06e354 · outbound

This paper cites an unresolved cited work.

Self-Composing Policies for Scalable Continual Reinforcement Learning Unresolved cited work

Reference 512

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:55:39.333468Z

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 03d52f89-da45-4ca9-aa3e-968d08590255 · outbound

This paper cites Conflict- averse gradient descent for multi-task learning.

Self-Composing Policies for Scalable Continual Reinforcement Learning Conflict- averse gradient descent for multi-task learning

Reference 1952

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.706409Z

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 993a1326-8f2f-417a-84b5-566c30dfb297 · outbound

This paper cites Building a subspace of policies for scalable continual learning.

Self-Composing Policies for Scalable Continual Reinforcement Learning Building a subspace of policies for scalable continual learning

Reference 1999

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.776482Z

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 a94b8a4a-42ed-40ac-8340-94c1eac3f064 · outbound

This paper cites D., Juraf- sky, D., et al.

Self-Composing Policies for Scalable Continual Reinforcement Learning D., Juraf- sky, D., et al

Reference 2009

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.811117Z

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 a8b89b48-f42c-401b-8d0b-1156bdeaed33 · outbound

This paper cites Curriculum learning.

Self-Composing Policies for Scalable Continual Reinforcement Learning Curriculum learning

Reference 2013

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.822258Z

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 a011d90e-6011-427b-a4aa-4868b87dc841 · outbound

This paper cites Progressive Neural Networks.

Self-Composing Policies for Scalable Continual Reinforcement Learning Progressive Neural Networks

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:39.106161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7744fc9b-bf68-445d-95e7-a0aef631af76 · outbound

This paper cites A., Veˇcer´ık, M., Roth¨orl, T., Heess, N., Pascanu, R., and Hadsell, R.

Self-Composing Policies for Scalable Continual Reinforcement Learning A., Veˇcer´ık, M., Roth¨orl, T., Heess, N., Pascanu, R., and Hadsell, R

Reference 2016

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.648531Z

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 208f7a10-c9d9-4c64-9bd9-f8a3d831883a · outbound

This paper cites Soft actor-critic: Off-policy maximum entropy deep reinforce- ment learning with a stochastic actor.

Self-Composing Policies for Scalable Continual Reinforcement Learning Soft actor-critic: Off-policy maximum entropy deep reinforce- ment learning with a stochastic actor

Reference 2017

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.753568Z

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 626cc428-a2d3-44ef-8a06-2ebd839fbf4a · outbound

This paper cites Don't forget, there is more than forgetting: new metrics for Continual Learning.

Self-Composing Policies for Scalable Continual Reinforcement Learning Don't forget, there is more than forgetting: new metrics for Continual Learning

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:39.047610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12c29cdb-6be0-44a5-9ffa-3db05fe64d27 · outbound

This paper cites W., Heess, N., Osindero, S., and Pascanu, R.

Self-Composing Policies for Scalable Continual Reinforcement Learning W., Heess, N., Osindero, S., and Pascanu, R

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.799539Z

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 eaa7c3c6-0804-454c-8758-75ec424bab0f · outbound

This paper cites an unresolved cited work.

Self-Composing Policies for Scalable Continual Reinforcement Learning Unresolved cited work

Reference 2020

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:55:39.833522Z

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 8e1bfe15-7c74-46a1-bc8b-e363508d15d1 · outbound

This paper cites N., Kaiser,Ł., and Polosukhin, I.

Self-Composing Policies for Scalable Continual Reinforcement Learning N., Kaiser,Ł., and Polosukhin, I

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.625070Z

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 a3fdf65c-1d57-4c0c-99c8-c73b6c679a50 · outbound

This paper cites Compacting, picking and growing for unforgetting continual learning.

Self-Composing Policies for Scalable Continual Reinforcement Learning Compacting, picking and growing for unforgetting continual learning

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.730466Z

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 40921fb1-adaa-4519-bde1-bd44063d3215 · outbound

This paper cites G., Menick, J., Munos, R., and Kavukcuoglu, K.

Self-Composing Policies for Scalable Continual Reinforcement Learning G., Menick, J., Munos, R., and Kavukcuoglu, K

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:39.764931Z

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

Observation 6ae13a21-2126-4b58-a649-085c98d14515 · inbound

Curriculum-Adapted Robust Reinforcement Learning for UAV Deconfliction in Adversarial Environments cites this paper.

Curriculum-Adapted Robust Reinforcement Learning for UAV Deconfliction in Adversarial Environments Self-Composing Policies for Scalable Continual Reinforcement Learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T22:43:20.198877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd4eb217-c347-4179-bb53-fdc3cfd694b9 · inbound

When Robots Sleep: Offline Skill Consolidation for Shared-Policy Robot Learning cites this paper.

When Robots Sleep: Offline Skill Consolidation for Shared-Policy Robot Learning Self-Composing Policies for Scalable Continual Reinforcement Learning

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-03T20:58:57.544492Z

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.