Paper Citation Record · LEDGER

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations

As of 23 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2501.12668.

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

pith.paper-citation-record.v1
2501.12668 v3

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T17:00:39.404564Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+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

24 of 24 outbound references displayed

verified exact0
verified fuzzy8
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 356a74c4-edf7-4426-b32a-c996890c4e7d · outbound

This paper cites Variational Option Discovery Algorithms.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Variational Option Discovery Algorithms

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.284426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a5f856b-89a9-4d64-aace-8ff73ecf8c79 · outbound

This paper cites Reinforcement Learning with NBDI In downstream learning, our objective is to learn a skill policy πθ(z|st) that maximizes the expected sum of discounted rewards, parameterized by θ.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Reinforcement Learning with NBDI In downstream learning, our objective is to learn a skill policy πθ(z|st) that maximizes the expected sum of discounted rewards, parameterized by θ

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:00:39.815397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0a825fa3-7dc9-4f25-83fd-7223025ca041 · outbound

This paper cites Hierarchical Few-Shot Imitation with Skill Transition Models.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Hierarchical Few-Shot Imitation with Skill Transition Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.309382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e98c0197-42c4-4961-822b-aa4f939e66bb · outbound

This paper cites Deep Successor Reinforcement Learning.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Deep Successor Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.319295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ae88fbb-def1-4a3c-8136-190aae601a21 · outbound

This paper cites Parrot: Data-Driven Behavioral Priors for Reinforcement Learning.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Parrot: Data-Driven Behavioral Priors for Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.360466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5c6dbcf-e155-416a-bfb6-54226364f196 · outbound

This paper cites The agent starts at the white point and aims to reach the red point.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations The agent starts at the white point and aims to reach the red point

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:00:39.796725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3aa4090e-ae0a-429a-8780-0928e906c805 · outbound

This paper cites Note that task and environment setup differ between the training data and the downstream task, demonstrating the model’s capacity to handle unseen downstream tasks.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Note that task and environment setup differ between the training data and the downstream task, demonstrating the model’s capacity to handle unseen downstream tasks

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:00:39.780037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e096401d-a79c-4272-b851-7e3688af8321 · outbound

This paper cites In the maze and sparse block stacking environment, a single fully-connected layer with hidden dimension 52 and 70 have been used, respectively.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations In the maze and sparse block stacking environment, a single fully-connected layer with hidden dimension 52 and 70 have been used, respectively

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:00:39.765484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 26ba5c93-b7d0-4a1b-96c8-7a4988efb30f · outbound

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

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Offline Reinforcement Learning with Implicit Q-Learning

Reference 1993

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.314060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3777762c-810c-4abc-9f7d-332f75ec639a · outbound

This paper cites Exploration by Random Network Distillation.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Exploration by Random Network Distillation

Reference 1994

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.295533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73f2092a-90a9-4955-ba5f-8eebce436c02 · outbound

This paper cites an unresolved cited work.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Unresolved cited work

Reference 1997

Resolution: unresolved; raw_fallback, observed 2026-08-10T17:00:39.835376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 131ef7c3-d7a5-457e-9e57-d18f5fe42b64 · outbound

This paper cites Mujoco: A physics engine for model-based control.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Mujoco: A physics engine for model-based control

Reference 1998

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:00:39.856047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 30ba7568-bd4b-4387-b138-9e2b5a9d5430 · outbound

This paper cites Q-cut—dynamic discovery of sub-goals in reinforcement learning.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Q-cut—dynamic discovery of sub-goals in reinforcement learning

Reference 2001

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:00:39.890122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 984b62c6-35aa-430a-b697-02ce6b3b832e · outbound

This paper cites Skill-based Meta-Reinforcement Learning.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Skill-based Meta-Reinforcement Learning

Reference 2002

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.334889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acdc3fa3-1cc9-4ea2-991f-9fa2ffed6108 · outbound

This paper cites Variational Intrinsic Control.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Variational Intrinsic Control

Reference 2003

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.304456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33e7d08d-7ea8-422b-a1d8-7557cdafc3f7 · outbound

This paper cites P., and Barto, A.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations P., and Barto, A

Reference 2004

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:00:39.872478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 50cf7c16-3959-491a-ae21-4eec5534cd17 · outbound

This paper cites URL https://doi.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations URL https://doi

Reference 2005

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.356602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 044f9e51-79e9-4135-a1a5-745a1f0ce861 · outbound

This paper cites TRAIL: Near-Optimal Imitation Learning with Suboptimal Data.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations TRAIL: Near-Optimal Imitation Learning with Suboptimal Data

Reference 2012

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.375264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee194b79-695a-4891-b1f6-e642eb3daf26 · outbound

This paper cites Eigenoption Discovery through the Deep Successor Representation.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Eigenoption Discovery through the Deep Successor Representation

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.325081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ebb9f36-1bc3-48b6-bb20-4d7db3969973 · outbound

This paper cites OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.289737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66e98dcc-5346-4e4a-85a7-c15980ea3dc4 · outbound

This paper cites Demonstration-Guided Reinforcement Learning with Learned Skills.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Demonstration-Guided Reinforcement Learning with Learned Skills

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.340097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fa293b8-4b3c-4717-9d21-9f2de7321e1e · outbound

This paper cites Option Discovery in Hierarchical Reinforcement Learning using Spatio-Temporal Clustering.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Option Discovery in Hierarchical Reinforcement Learning using Spatio-Temporal Clustering

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-10T17:00:39.364979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6eb3ddb-7587-4d19-a166-2aef55ca556d · outbound

This paper cites Investigating the effectiveness of bpe: The power of shorter sequences.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations Investigating the effectiveness of bpe: The power of shorter sequences

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:00:39.905139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6ffefef2-e886-4bfb-adc1-3e990a54a59e · outbound

This paper cites MO2: Model-Based Offline Options.

NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations MO2: Model-Based Offline Options

Reference 2022

Resolution: metadata mismatch; local_arxiv, observed 2026-08-10T17:00:39.595870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Pith citing papers

No inbound Pith citation observations are available.