Paper Citation Record · LEDGER

Efficient Hypergradient Descent for Inverse Reinforcement Learning

As of 19 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2608.11052.

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

pith.paper-citation-record.v1
2608.11052 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T11:26:02.942258Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+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

15 of 15 outbound references displayed

verified exact5
verified fuzzy5
unresolved4
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 28a544c9-ce1c-46a3-9b4c-2e9a0bb31ec3 · outbound

This paper cites Therefore, αDKL(epπθ ∥epϕ) =E τ∼epπθ " ∞X t=1 (αlogπ θ(at |s t)−r ϕ(st, at)) # +αlogZ ϕ.

Efficient Hypergradient Descent for Inverse Reinforcement Learning Therefore, αDKL(epπθ ∥epϕ) =E τ∼epπθ " ∞X t=1 (αlogπ θ(at |s t)−r ϕ(st, at)) # +αlogZ ϕ

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:26:03.543094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8d26906d-e9d7-4351-9676-5ae542388b98 · outbound

This paper cites ∞X t=1 γt−1 logπ θ(at |s t) # =−E τ∼p expert.

Efficient Hypergradient Descent for Inverse Reinforcement Learning ∞X t=1 γt−1 logπ θ(at |s t) # =−E τ∼p expert

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:26:03.530082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 99918331-970a-4806-b099-f850cac23993 · outbound

This paper cites Natural hypergradient de- scent: Algorithm design, convergence analysis, and parallel implementation.arXiv preprint arXiv:2602.10905,.

Efficient Hypergradient Descent for Inverse Reinforcement Learning Natural hypergradient de- scent: Algorithm design, convergence analysis, and parallel implementation.arXiv preprint arXiv:2602.10905,

Reference 6

Resolution: verified exact; raw_fallback, observed 2026-08-12T11:26:03.319693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a6300e82-9013-4f85-b8f3-27690ad68883 · outbound

This paper cites Natural Policy Gradients In Reinforcement Learning Explained.

Efficient Hypergradient Descent for Inverse Reinforcement Learning Natural Policy Gradients In Reinforcement Learning Explained

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-08-12T11:26:03.105051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a2d1dcd2-a8ef-4ae1-8586-5ac449da702a · outbound

This paper cites ∂g ∂θ θ⋆(ϕ),ϕ #−1 ∂g ∂ϕ θ⋆(ϕ),ϕ . Since ∂g ∂θ = ∂2Linner ∂θ 2 , ∂g ∂ϕ = ∂2Linner ∂θ∂ϕ , we get dθ⋆ dϕ ϕ =−.

Efficient Hypergradient Descent for Inverse Reinforcement Learning ∂g ∂θ θ⋆(ϕ),ϕ #−1 ∂g ∂ϕ θ⋆(ϕ),ϕ . Since ∂g ∂θ = ∂2Linner ∂θ 2 , ∂g ∂ϕ = ∂2Linner ∂θ∂ϕ , we get dθ⋆ dϕ ϕ =−

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:26:03.554667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 835c4e51-022e-47ac-b652-c035985b099a · outbound

This paper cites ∞X t=1 gt(τ)g t(τ) ⊤ # . Finally, applying Lemma 4.1 componentwise gives Eτ∼epπθ.

Efficient Hypergradient Descent for Inverse Reinforcement Learning ∞X t=1 gt(τ)g t(τ) ⊤ # . Finally, applying Lemma 4.1 componentwise gives Eτ∼epπθ

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:26:03.516484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 77b36f46-a84c-4f6c-8c3f-4d103b32b54e · outbound

This paper cites Souradip Chakraborty, Amrit Bedi, Alec Koppel, Huazheng Wang, Dinesh Manocha, Mengdi Wang, and Furong Huang.

Efficient Hypergradient Descent for Inverse Reinforcement Learning Souradip Chakraborty, Amrit Bedi, Alec Koppel, Huazheng Wang, Dinesh Manocha, Mengdi Wang, and Furong Huang

Reference 2014

Resolution: metadata mismatch; raw_fallback, observed 2026-08-12T11:26:03.505054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c70af340-f658-41db-9ef7-2cf63e31a3b2 · outbound

This paper cites Rank-1 ap- proximation of inverse fisher for natural policy gradients in deep reinforcement learning.arXiv preprint arXiv:2601.18626,.

Efficient Hypergradient Descent for Inverse Reinforcement Learning Rank-1 ap- proximation of inverse fisher for natural policy gradients in deep reinforcement learning.arXiv preprint arXiv:2601.18626,

Reference 2015

Resolution: verified exact; raw_fallback, observed 2026-08-12T11:26:03.397415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d5f7b85f-c790-4f6b-be2c-172610441a12 · outbound

This paper cites Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity.

Efficient Hypergradient Descent for Inverse Reinforcement Learning Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-12T11:26:02.922372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f09e1a8-f956-4cb0-b6ec-e6f769f93771 · outbound

This paper cites Frequent Directions : Simple and Deterministic Matrix Sketching.

Efficient Hypergradient Descent for Inverse Reinforcement Learning Frequent Directions : Simple and Deterministic Matrix Sketching

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-12T11:26:02.897810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53da9989-9480-4f50-bfb5-83c2cef374ac · outbound

This paper cites Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review.

Efficient Hypergradient Descent for Inverse Reinforcement Learning Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-12T11:26:02.909932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 444421fd-0641-4f09-ab05-109e196003cc · outbound

This paper cites Explaining and Preventing Alignment Collapse in Iterative RLHF.

Efficient Hypergradient Descent for Inverse Reinforcement Learning Explaining and Preventing Alignment Collapse in Iterative RLHF

Reference 2020

Resolution: verified exact; local_arxiv, observed 2026-08-12T11:26:03.437865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 239f0717-51cb-4e91-9462-21904e9e9e82 · outbound

This paper cites Then the gradient of the induced outer objective eLouter(ϕ) :=L outer(θ⋆(ϕ)) is given by ∇ϕ eLouter ϕ =− ∂2Linner ∂ϕ∂θ θ⋆(ϕ),ϕ " ∂2Linner ∂θ 2 θ⋆(ϕ),ϕ #−1 ∇θLouter|θ⋆(ϕ).

Efficient Hypergradient Descent for Inverse Reinforcement Learning Then the gradient of the induced outer objective eLouter(ϕ) :=L outer(θ⋆(ϕ)) is given by ∇ϕ eLouter ϕ =− ∂2Linner ∂ϕ∂θ θ⋆(ϕ),ϕ " ∂2Linner ∂θ 2 θ⋆(ϕ),ϕ #−1 ∇θLouter|θ⋆(ϕ)

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T11:26:03.568289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e58c82b5-d24e-49e6-9a5d-35eefb8e4fc7 · outbound

This paper cites Scalable linucb: Low-rank design matrix updates for recommenders with large action spaces.arXiv preprint arXiv:2510.19349,.

Efficient Hypergradient Descent for Inverse Reinforcement Learning Scalable linucb: Low-rank design matrix updates for recommenders with large action spaces.arXiv preprint arXiv:2510.19349,

Reference 2025

Resolution: verified exact; raw_fallback, observed 2026-08-12T11:26:03.214880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b77cffe1-f9a4-4743-bc39-6893c3c913f5 · outbound

This paper cites Approximation Methods for Bilevel Programming.

Efficient Hypergradient Descent for Inverse Reinforcement Learning Approximation Methods for Bilevel Programming

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-12T11:26:02.893846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.