Paper Citation Record · LEDGER

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning

As of 10 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 3 inbound Pith citation observations for arXiv:2502.02332.

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

pith.paper-citation-record.v1
2502.02332 v2

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T12:41:16.343541Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:21:39.299158Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-10T07:37:04.719767Z

Reference resolution

28 of 28 outbound references displayed

verified exact7
verified fuzzy8
unresolved12
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 83a894ad-c0cc-443e-803a-3fbe0796018d · outbound

This paper cites A Moreau Envelope Approach for LQR Meta-Policy Estimation.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning A Moreau Envelope Approach for LQR Meta-Policy Estimation

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-09T12:41:16.612679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 769b3d2b-abaa-491b-9c15-3297e53bf845 · outbound

This paper cites In addition, since the tasks Tj ∈ Mand samples u ∼ Sr are drawn independently, we can use Lemma 3 to control ∥∇ ˜J(θ) − e∇J(θ)∥.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning In addition, since the tasks Tj ∈ Mand samples u ∼ Sr are drawn independently, we can use Lemma 3 to control ∥∇ ˜J(θ) − e∇J(θ)∥

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:41:16.699807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f211665e-8452-4eed-b456-84b9c23f6d99 · outbound

This paper cites Convergence of Gradient-based MAML in LQR.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Convergence of Gradient-based MAML in LQR

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-09T12:41:16.568537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d1ca02f1-a0f4-4e97-8ac8-47f4619e50aa · outbound

This paper cites On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-09T12:41:16.518542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3878cfaf-8ffb-4473-9ad2-9dc6edbae164 · outbound

This paper cites ES-MAML: Simple Hessian-Free Meta Learning.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning ES-MAML: Simple Hessian-Free Meta Learning

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-09T12:41:16.504815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 193b88e8-d9d9-4c97-802c-630697e45e68 · outbound

This paper cites an unresolved cited work.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-09T12:41:16.743461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f590d168-8a52-478d-b5e2-005fb8743c75 · outbound

This paper cites Todorov, T.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Todorov, T

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:41:16.735238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8d3f7c0a-c14d-4f2b-9000-024cde167d65 · outbound

This paper cites Asynchronous Heterogeneous Linear Quadratic Regulator Design.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Asynchronous Heterogeneous Linear Quadratic Regulator Design

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T12:41:16.313536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bbc1440-88e4-4b5c-8f6e-a619151f96fe · outbound

This paper cites Model-free Learning with Heterogeneous Dynamical Systems: A Federated LQR Approach.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Model-free Learning with Heterogeneous Dynamical Systems: A Federated LQR Approach

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T12:41:16.317786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e08c7a4-f181-422c-a174-e211a0047564 · outbound

This paper cites Learning to reinforcement learn.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Learning to reinforcement learn

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T12:41:16.321039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93e3e295-2284-4bc7-9c67-c79d23b8c133 · outbound

This paper cites Preparing for the Unknown: Learning a Universal Policy with Online System Identification.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Preparing for the Unknown: Learning a Universal Policy with Online System Identification

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T12:41:16.327376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e65bbd3d-9c58-443b-985f-8e633cfa548a · outbound

This paper cites an unresolved cited work.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-09T12:41:16.726379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fdef6025-f4a8-46eb-af6e-e9eba6dc0df0 · outbound

This paper cites Similarly, we consider a zeroth-order estimation of the task-specific and meta-gradients.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Similarly, we consider a zeroth-order estimation of the task-specific and meta-gradients

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:41:16.717525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0c3ee682-260a-4157-b3b6-76d762456184 · outbound

This paper cites In particular, Zhan and Anderson (2024) does not focus on RL tasks and approximates gradients using the pre-activation outputs of the last layer for classification tasks.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning In particular, Zhan and Anderson (2024) does not focus on RL tasks and approximates gradients using the pre-activation outputs of the last layer for classification tasks

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:41:16.708357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 541fb82d-e91d-40e8-bd93-ed2b6d521514 · outbound

This paper cites In particular, by (Nemhauser et al., 1978, Section 4), we know that the value of the greedy optimization is close to the optimal as F (S) ≥ (1 − e−1)F (S ⋆).

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning In particular, by (Nemhauser et al., 1978, Section 4), we know that the value of the greedy optimization is close to the optimal as F (S) ≥ (1 − e−1)F (S ⋆)

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:41:16.691779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d16211cd-049a-426d-98ec-920c9391e652 · outbound

This paper cites Local SGD Converges Fast and Communicates Little.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Local SGD Converges Fast and Communicates Little

Reference 1972

Resolution: unresolved; no resolver link, observed 2026-08-09T12:41:16.304744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 717ff867-224f-405a-96f1-d1756a0b97e8 · outbound

This paper cites RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning

Reference 1977

Resolution: unresolved; no resolver link, observed 2026-08-09T12:41:16.262932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6891ec4a-d16d-4268-b9fb-a4ff3513d739 · outbound

This paper cites Towards Sustainable Learning: Coresets for Data-efficient Deep Learning.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Towards Sustainable Learning: Coresets for Data-efficient Deep Learning

Reference 1982

Resolution: verified exact; local_arxiv, observed 2026-08-09T12:41:16.382388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 31580378-edfb-42fa-aa61-c4e5240a3e25 · outbound

This paper cites Ghadirzadeh, X.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Ghadirzadeh, X

Reference 2004

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:41:16.760488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e4147cd9-8d15-42da-8611-1c2d17d3361b · outbound

This paper cites an unresolved cited work.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Unresolved cited work

Reference 2012

Resolution: malformed identifier; no resolver link, observed 2026-08-09T12:41:16.310440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20a48c14-9dd9-4d01-85ed-f346d38eecbc · outbound

This paper cites Online convex optimization in the bandit setting: gradient descent without a gradient.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Online convex optimization in the bandit setting: gradient descent without a gradient

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-09T12:41:16.266680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 950b26bd-ec76-43cb-863a-d75dede55322 · outbound

This paper cites Evolution Strategies as a Scalable Alternative to Reinforcement Learning.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Evolution Strategies as a Scalable Alternative to Reinforcement Learning

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-09T12:41:16.293835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60afd4cf-fc84-425b-a81b-d6378224086c · outbound

This paper cites Model-Agnostic Zeroth-Order Policy Optimization for Meta-Learning of Ergodic Linear Quadratic Regulators.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Model-Agnostic Zeroth-Order Policy Optimization for Meta-Learning of Ergodic Linear Quadratic Regulators

Reference 2019

Resolution: verified exact; local_arxiv, observed 2026-08-09T12:41:16.546856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e677a2c4-bb87-46bd-b14d-80941775f01e · outbound

This paper cites Molybog and J.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Molybog and J

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:41:16.751760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3e18d678-9ac9-4c17-b79d-6a338a50c806 · outbound

This paper cites Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Control.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Control

Reference 2021

Resolution: verified exact; local_arxiv, observed 2026-08-09T12:41:16.582194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 43842f06-ef58-4d52-8548-fe6d27187a1d · outbound

This paper cites ProMP: Proximal Meta-Policy Search.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning ProMP: Proximal Meta-Policy Search

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-09T12:41:16.290464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97f5af7c-3914-408f-b80e-0b889800e6a0 · outbound

This paper cites Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-09T12:41:16.283396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0db18d1-6b0e-4977-b53c-8e3a994c9eae · outbound

This paper cites Arndt, M.

Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning Arndt, M

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:41:16.768753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation 2917b736-4708-4d6c-a94e-839588e3bc20 · inbound

The Role of Diversity in In-Context Learning for Large Language Models cites this paper.

The Role of Diversity in In-Context Learning for Large Language Models Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T14:21:39.299158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f129d589-0c70-4fce-9cee-63627b49746a · inbound

On the Gradient Domination of the LQG Problem cites this paper.

On the Gradient Domination of the LQG Problem Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T18:20:57.142267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf50c772-4d04-4a30-a485-46555d042a65 · inbound

Multitask LQG Control: Performance and Generalization Bounds cites this paper.

Multitask LQG Control: Performance and Generalization Bounds Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-10T07:37:04.721129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.