Paper Citation Record · LEDGER

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning

As of 5 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2605.16318.

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

pith.paper-citation-record.v1
2605.16318 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T23:26:23.989545Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+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

29 of 29 outbound references displayed

verified exact10
verified fuzzy14
unresolved5
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 07b1ec12-0b96-4af1-95b2-dac0328eb953 · outbound

This paper cites An overview and comparative analysis of Recurrent Neural Networks for Short Term Load Forecasting.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning An overview and comparative analysis of Recurrent Neural Networks for Short Term Load Forecasting

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:29:13.179830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 11b98cc0-c2a1-4692-9537-46a065a54194 · outbound

This paper cites OpenAI Gym.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning OpenAI Gym

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:29:13.160678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5c8ff4fd-aa8c-4778-9254-baa17cb0f253 · outbound

This paper cites Chandar, C.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Chandar, C

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.567256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e3735a47-7baf-4869-82ba-8a8ac45b1529 · outbound

This paper cites Chung, C.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Chung, C

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.541077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a7124105-e1db-418a-8ef2-3c4ffd68ad8e · outbound

This paper cites Continual Backprop: Stochastic Gradient Descent with Persistent Randomness.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Continual Backprop: Stochastic Gradient Descent with Persistent Randomness

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:29:13.173673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cbfaa98f-9180-48aa-8e68-960c45fa1f57 · outbound

This paper cites Memory-based control with recurrent neural networks.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Memory-based control with recurrent neural networks

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:29:13.168177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 32c14023-889c-4251-8fce-075b731d13a6 · outbound

This paper cites Don't Unroll Adjoint: Differentiating SSA-Form Programs.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Don't Unroll Adjoint: Differentiating SSA-Form Programs

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:29:13.185651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2b12283a-765b-4d13-90ad-dbcef41d2a4d · outbound

This paper cites Visualizing and Understanding Recurrent Networks.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Visualizing and Understanding Recurrent Networks

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:29:13.155625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 72b82647-fe2e-41a6-a433-c989798fea99 · outbound

This paper cites A Practical Sparse Approximation for Real Time Recurrent Learning.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning A Practical Sparse Approximation for Real Time Recurrent Learning

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:29:13.190992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8f2be63f-6fd4-48df-b4cb-08a44c0f50bc · outbound

This paper cites Parisotto, F.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Parisotto, F

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.583943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 50019752-118e-442d-9c70-e9c74793f8ac · outbound

This paper cites Learning Agent State Online with Recurrent Generate-and-Test.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Learning Agent State Online with Recurrent Generate-and-Test

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:29:13.147238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 06e69e47-ee96-4cf7-b25f-81b0f006a00b · outbound

This paper cites Learning to Predict Independent of Span.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Learning to Predict Independent of Span

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:29:13.138502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9e87f9dc-bb93-49e0-abdb-ee630646aa6f · outbound

This paper cites Vaswani, N.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Vaswani, N

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.536964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 20b36415-69e6-4bcf-a3b1-1be34dc60d37 · outbound

This paper cites On Improving Deep Reinforcement Learning for POMDPs.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning On Improving Deep Reinforcement Learning for POMDPs

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:29:13.197038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 21325ec6-0e69-4a41-a5e8-dc91b3b6f09f · outbound

This paper cites an unresolved cited work.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-05-20T23:34:14.597571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e252bdce-3a65-4d68-96c8-0c2a479c7ea4 · outbound

This paper cites in an experience replay buffer), they must also continually incorporate the newest information into their decisions (i.e.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning in an experience replay buffer), they must also continually incorporate the newest information into their decisions (i.e

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.532540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c74618e6-0726-4f86-8bde-e50ac20fd02a · outbound

This paper cites an unresolved cited work.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-05-20T23:34:14.547425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 81db78f9-b71b-4cc8-9672-ba8b9f72f0fd · outbound

This paper cites They show improvement in several settings, but don’t explore the model when starved for temporal information in the update.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning They show improvement in several settings, but don’t explore the model when starved for temporal information in the update

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.527390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3c949341-3e85-41b1-b7f2-75178f519531 · outbound

This paper cites One can even change the requirements on the architecture in terms of final objectives.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning One can even change the requirements on the architecture in terms of final objectives

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.552544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 19510957-f2f1-464f-8542-d381f8c2660b · outbound

This paper cites reservoir.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning reservoir

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.601773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 74957301-d485-4fd2-a403-f714e7c50f93 · outbound

This paper cites an unresolved cited work.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-05-20T23:34:14.510857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a83f4d97-2bd5-48ba-bb71-e1c9fae9fbba · outbound

This paper cites Because of these compromises, it is still unclear if transformers are a viable solution to the state construction problem in continual reinforcement learning.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Because of these compromises, it is still unclear if transformers are a viable solution to the state construction problem in continual reinforcement learning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.557723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 386cec15-bac5-4c62-8bf9-1165249db3df · outbound

This paper cites an unresolved cited work.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-05-20T23:34:14.593023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 752920eb-8f7e-491a-b271-43a0b5b35ab9 · outbound

This paper cites We use a third strategy here (using gradient information to refresh the hidden state to minimize the objective), but found little difference between this and the stale approach.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning We use a third strategy here (using gradient information to refresh the hidden state to minimize the objective), but found little difference between this and the stale approach

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.516453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f8bc8c17-8e22-4714-a841-19b731939e28 · outbound

This paper cites As compared to the additive and multiplicative the mixture of experts RNN network performs in-between the two networks.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning As compared to the additive and multiplicative the mixture of experts RNN network performs in-between the two networks

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.588681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e08fde7c-36ab-4479-913d-2210aa82ea94 · outbound

This paper cites For DirectionalTMaze the AAGRU and MAGRU have a reasonable median performance.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning For DirectionalTMaze the AAGRU and MAGRU have a reasonable median performance

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.562413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 74909077-031d-4486-9288-bc298bab9124 · outbound

This paper cites Overall, we found the size of the encoding network to not make a large difference in the final performance.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Overall, we found the size of the encoding network to not make a large difference in the final performance

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.577422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ea9d5c2a-acee-47bb-9ebd-5ee1173476b4 · outbound

This paper cites an unresolved cited work.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-05-20T23:34:14.572914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d1823429-27dc-435f-a05c-cb81b82086a8 · outbound

This paper cites Line is the median over 1000 episodes, with the shaded region as the 1st and 3rd quantile over the same window.

Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning Line is the median over 1000 episodes, with the shaded region as the 1st and 3rd quantile over the same window

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:34:14.522162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

No inbound Pith citation observations are available.