Paper Citation Record · LEDGER

Online Learning in MDPs with Partially Adversarial Transitions and Losses

As of 9 August 2026, this Paper Citation Record lists 10 of 10 outbound references and 0 inbound Pith citation observations for arXiv:2602.09474.

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

pith.paper-citation-record.v1
2602.09474 v2

Coverage vector

measured 10 of 10 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T03:01:40.909364Z

measured 10 of 10 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

10 of 10 outbound references displayed

verified exact0
verified fuzzy0
unresolved8
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation dade1b98-4bbb-42b9-9df5-5655a500dcce · outbound

This paper cites We’ll now proveG 4 is true w.p at least 1−δ.

Online Learning in MDPs with Partially Adversarial Transitions and Losses We’ll now proveG 4 is true w.p at least 1−δ

Reference 1

Resolution: malformed identifier; no resolver link, observed 2026-08-03T03:01:40.287853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ba61a41-0bc5-4473-9d3d-5e6c635a333a · outbound

This paper cites Online learning in episodic markovian decision processes by relative entropy policy search.

Online Learning in MDPs with Partially Adversarial Transitions and Losses Online learning in episodic markovian decision processes by relative entropy policy search

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T03:01:40.064946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1eabc990-6bea-46e8-9fcd-411e857fe43b · outbound

This paper cites an unresolved cited work.

Online Learning in MDPs with Partially Adversarial Transitions and Losses Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T03:01:40.368373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 694328ff-cfee-4c8e-96fd-774cc1636c45 · outbound

This paper cites an unresolved cited work.

Online Learning in MDPs with Partially Adversarial Transitions and Losses Unresolved cited work

Reference 8

Resolution: malformed identifier; no resolver link, observed 2026-08-03T03:01:40.556561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d3009bd-3173-443b-945c-3b7115547b65 · outbound

This paper cites qpk,πk h (s, a)− X c∈Ch ˆµk h(s, a, c)ϱk(c) ! ¯ℓk h(s, a) # (tower rule) = X k,h,s,a Ek.

Online Learning in MDPs with Partially Adversarial Transitions and Losses qpk,πk h (s, a)− X c∈Ch ˆµk h(s, a, c)ϱk(c) ! ¯ℓk h(s, a) # (tower rule) = X k,h,s,a Ek

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T03:01:40.751409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1243624-b570-4126-86c0-c88a71ccca3d · outbound

This paper cites bandit decision step.

Online Learning in MDPs with Partially Adversarial Transitions and Losses bandit decision step

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T03:01:40.909364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92a4e4db-fb0b-483f-8397-5d901eba3fcc · outbound

This paper cites That is, a tuple (s, a, s′) for each step inΛ h.

Online Learning in MDPs with Partially Adversarial Transitions and Losses That is, a tuple (s, a, s′) for each step inΛ h

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-03T03:01:40.202680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29c0e365-0bf4-4273-9e28-0bcf44422b12 · outbound

This paper cites Corruption-robust exploration in episodic reinforcement learning.

Online Learning in MDPs with Partially Adversarial Transitions and Losses Corruption-robust exploration in episodic reinforcement learning

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-03T03:01:39.214140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 316ee0d0-ef26-477e-a2f0-174e4c21f9b2 · outbound

This paper cites an unresolved cited work.

Online Learning in MDPs with Partially Adversarial Transitions and Losses Unresolved cited work

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T03:01:39.734586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fe8e462-4df1-4cd4-be59-fd0cd6758d7a · outbound

This paper cites Model-Free Non-Stationary RL: Near-Optimal Regret and Applications in Multi-Agent RL and Inventory Control.

Online Learning in MDPs with Partially Adversarial Transitions and Losses Model-Free Non-Stationary RL: Near-Optimal Regret and Applications in Multi-Agent RL and Inventory Control

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-03T03:01:39.324907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.