Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning | Paper Citation Record

Observation 5c9b08b0-f94a-4f7f-b4b9-df0db07a352a · outbound

This paper cites Deep reinforcement learning for financial trading using multi-modal features.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Deep reinforcement learning for financial trading using multi-modal features

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.589852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2194d1bb-e10c-4a9a-ac98-7f8082d4b27d · outbound

This paper cites Vulnerability of deep reinforcement learning to policy induction attacks.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Vulnerability of deep reinforcement learning to policy induction attacks

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.577529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e589d91b-b27d-4cd0-a5b1-44349fb3e6c1 · outbound

This paper cites Simple physical adver- sarial examples against end-to-end autonomous driving models.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Simple physical adver- sarial examples against end-to-end autonomous driving models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.565481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 87b4f1b1-5d6d-4634-af1f-027fa7513b2c · outbound

This paper cites Dynamic regret of policy optimization in non-stationary environments.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Dynamic regret of policy optimization in non-stationary environments

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.553656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b5b46856-d2b2-4da0-ab76-11c9482968d0 · outbound

This paper cites Execute Order 66: Targeted Data Poisoning for Reinforcement Learning.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Execute Order 66: Targeted Data Poisoning for Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.587112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1754716b-14f1-437f-9902-4be21b8fdb2d · outbound

This paper cites Addressing function approximation error in actor-critic methods.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Addressing function approximation error in actor-critic methods

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.591968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85c030a6-cd4c-4eb7-95d3-0642087f9480 · outbound

This paper cites A practical guide to multi-objective reinforcement learning and planning.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning A practical guide to multi-objective reinforcement learning and planning

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.535047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5e9eab07-bf96-4438-b3fa-47cf2925cfed · outbound

This paper cites Financial Trading as a Game: A Deep Reinforcement Learning Approach.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Financial Trading as a Game: A Deep Reinforcement Learning Approach

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.610643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f99fba14-75ce-41e5-bd02-1e543e906158 · outbound

This paper cites Adversarial Attacks on Neural Network Policies.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Adversarial Attacks on Neural Network Policies

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.615717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a74b81ed-1ddd-408f-822c-24ee89350b11 · outbound

This paper cites Deceptive reinforcement learning under adversarial manipulations on cost signals.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Deceptive reinforcement learning under adversarial manipulations on cost signals

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.523009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 15cb4463-26a6-4346-8047-a53d7412e39a · outbound

This paper cites Challenges and countermeasures for adversarial attacks on deep reinforcement learning.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Challenges and countermeasures for adversarial attacks on deep reinforcement learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.624542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 440ba23b-acb8-4b6f-b886-aeeb56b3db64 · outbound

This paper cites Deep reinforcement learning for autonomous driving: A survey.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Deep reinforcement learning for autonomous driving: A survey

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.628720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efd045a2-8c08-4dd4-9f9d-d1ee1d296d66 · outbound

This paper cites Query-based targeted action- space adversarial policies on deep reinforcement learning agents.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Query-based targeted action- space adversarial policies on deep reinforcement learning agents

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.496355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 831ec55c-9f2a-430b-81a0-c6a81200a16b · outbound

This paper cites Spatiotemporally constrained action space attacks on deep reinforcement learning agents.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Spatiotemporally constrained action space attacks on deep reinforcement learning agents

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.484719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 83e8a710-3f69-419e-af75-99e964dccc54 · outbound

This paper cites Continuous control with deep reinforcement learning.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Continuous control with deep reinforcement learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.641740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed6e120d-bc8b-47f4-8dc0-9e97ebf29361 · outbound

This paper cites Tactics of Adversarial Attack on Deep Reinforcement Learning Agents.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Tactics of Adversarial Attack on Deep Reinforcement Learning Agents

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.647318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 972aedc4-229b-46ec-93e9-4f9b700432a8 · outbound

This paper cites Provably efficient black-box action poisoning attacks against reinforcement learning.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Provably efficient black-box action poisoning attacks against reinforcement learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.654742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbed4a31-c0d8-49c2-8243-8c732c1ecfbd · outbound

This paper cites Efficient adversarial attacks on online multi-agent reinforcement learning.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Efficient adversarial attacks on online multi-agent reinforcement learning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.465765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5250666e-5dfc-4c77-93f0-189da10bc084 · outbound

This paper cites Data poisoning attacks in contextual bandits.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Data poisoning attacks in contextual bandits

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.453931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8c586906-bef4-4a40-ac42-df693a73d6c3 · outbound

This paper cites Policy poisoning in batch reinforcement learning and control.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Policy poisoning in batch reinforcement learning and control

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.667933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60ec42e5-d81b-47b2-9098-175a027d6158 · outbound

This paper cites Disturbing Reinforcement Learning Agents with Corrupted Rewards.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Disturbing Reinforcement Learning Agents with Corrupted Rewards

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-12T16:55:50.941231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d5ee7621-6529-4315-940b-8faba8c76577 · outbound

This paper cites Inverse filtering for hidden markov models with applications to counter-adversarial autonomous systems.IEEE Transactions on Signal Processing, 68:4987–5002, 2020.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Inverse filtering for hidden markov models with applications to counter-adversarial autonomous systems.IEEE Transactions on Signal Processing, 68:4987–5002, 2020

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.435204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation bf150143-5bea-4a9d-b675-1e4a10f6b13e · outbound

This paper cites Optimal attack and defense for reinforcement learning.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Optimal attack and defense for reinforcement learning

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.423657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8f96afad-9eaa-4624-b933-8d6abc192d86 · outbound

This paper cites Characterizing Attacks on Deep Reinforcement Learning.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Characterizing Attacks on Deep Reinforcement Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.684372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a595077-d822-4ed5-a9b3-6d0fe9cd7b76 · outbound

This paper cites Continuous state-space models for optimal sepsis treatment: a deep reinforcement learning approach.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Continuous state-space models for optimal sepsis treatment: a deep reinforcement learning approach

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.412199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5a11c408-7de9-4fce-b400-350d3dec5088 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Proximal Policy Optimization Algorithms

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.693847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90e98eec-8362-489a-9bbe-2eabd7fae982 · outbound

This paper cites Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.697615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c274a7d4-faae-40cb-86d1-75e4904bbd0f · outbound

This paper cites Robustifying reinforcement learning agents via action space adversarial training.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Robustifying reinforcement learning agents via action space adversarial training

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.399984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 100b06c0-d12c-43b4-a56f-33223b70a094 · outbound

This paper cites Adversarial black-box attacks on vision-based deep reinforcement learning agents.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Adversarial black-box attacks on vision-based deep reinforcement learning agents

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.385637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b8baee31-b61d-4f9a-9763-5763eea20cc2 · outbound

This paper cites Action robust reinforcement learning and applications in continuous control.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Action robust reinforcement learning and applications in continuous control

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.372625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation cd1d1718-5f70-4e18-81da-564c2b341a2d · outbound

This paper cites Freedman’s inequality for matrix martingales.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Freedman’s inequality for matrix martingales

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.360307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation bf9367eb-1240-49ab-bbd5-937ee82bc7d3 · outbound

This paper cites Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-12T16:55:50.884663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6488b0a3-0aeb-4d06-a092-aa257a7d2d93 · outbound

This paper cites Transferable environment poisoning: Training-time attack on reinforcement learning.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Transferable environment poisoning: Training-time attack on reinforcement learning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.348530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5b8915fd-f881-4d8c-b77d-74d7528dd889 · outbound

This paper cites Prediction- guided multi-objective reinforcement learning for continuous robot control.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Prediction- guided multi-objective reinforcement learning for continuous robot control

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.336198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2da10514-5ebc-4834-a531-4dc1bb611ce4 · outbound

This paper cites Enhanced adversarial strategically-timed attacks against deep reinforcement learning.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Enhanced adversarial strategically-timed attacks against deep reinforcement learning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.323500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 23a793b4-5c98-4410-b47f-efa4cb3d904f · outbound

This paper cites Reinforcement learning in healthcare: A survey.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Reinforcement learning in healthcare: A survey

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.742968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfd34c65-561e-4b53-b2ea-562122a737f2 · outbound

This paper cites Robust Reinforcement Learning on State Observations with Learned Optimal Adversary.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Robust Reinforcement Learning on State Observations with Learned Optimal Adversary

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T16:55:50.748765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b4a6a1b-9d95-4bdb-8c05-d34084839453 · outbound

This paper cites Adaptive reward-poisoning attacks against reinforcement learning.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Adaptive reward-poisoning attacks against reinforcement learning

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.300627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d13c121c-cb27-41a2-ac3b-2b828734e488 · outbound

This paper cites an unresolved cited work.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:55:51.285430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 461c5c04-2bb3-4adb-8613-58b756f222ef · outbound

This paper cites For episode k, V o 1(sk.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning For episode k, V o 1(sk

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.271055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6bb0762c-fe4a-429d-9b3e-d1f8d5483635 · outbound

This paper cites an unresolved cited work.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:55:51.258178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f7bc9275-1bc8-46ec-abf7-96355b336827 · outbound

This paper cites = E " HX h=1 ∆ k h|F k 1 # where F k h represents the σ-field generated by all the random variables until episode k, step h begins.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning = E " HX h=1 ∆ k h|F k 1 # where F k h represents the σ-field generated by all the random variables until episode k, step h begins

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.245807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fb27b520-79d3-4255-935a-1dc9620c62eb · outbound

This paper cites (9) Next, we will show that with a probability at least 1 − δ2, we have KX k=1 HX h=1 ∆ k h ≤ KX k=1 V o 1(sk.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning (9) Next, we will show that with a probability at least 1 − δ2, we have KX k=1 HX h=1 ∆ k h ≤ KX k=1 V o 1(sk

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.230722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8595aea2-ba7a-48bb-a698-bb86503f6044 · outbound

This paper cites (10) Since E hPH h=1 ∆ k h|F k 1 i = V o 1(sk.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning (10) Since E hPH h=1 ∆ k h|F k 1 i = V o 1(sk

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.198701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c1ba3183-1edb-4fed-a9d5-272fd0b31cd1 · outbound

This paper cites an unresolved cited work.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:55:51.185502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7d369ba3-877b-4523-ac47-a23b6aaaccf5 · outbound

This paper cites an unresolved cited work.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:55:51.171717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fe41ac63-ffce-461e-a375-7082a7728cd8 · outbound

This paper cites HX h=1 ∆ k h 2 |F k 1 # ≤ H 2 KX k=1 E.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning HX h=1 ∆ k h 2 |F k 1 # ≤ H 2 KX k=1 E

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.155576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 57917e03-baee-47e2-bca0-d36a03da0e1a · outbound

This paper cites (13) By Freeman’s inequality [31], we have P  YK = KX k=1 Xk > 2H 2 vuutln(1/δ2) KX k=1 V o 1(sk.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning (13) By Freeman’s inequality [31], we have P  YK = KX k=1 Xk > 2H 2 vuutln(1/δ2) KX k=1 V o 1(sk

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.141215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a6ec0305-8d00-43bb-a4c3-cdf0b23251ad · outbound

This paper cites an unresolved cited work.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:55:51.122201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7e269d5c-6b2b-4b95-b03d-f42cf22fbdda · outbound

This paper cites an unresolved cited work.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:55:51.108814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation bd38d6e0-ae72-4159-8703-d18999918267 · outbound

This paper cites 2βh k (T h D,I (k), δ1)2T h D,I (k)2 −T h D,I (k)(H − h + 1)2 # = HX h=1 MX m=1 X (D,I )∈T h k kX T h D,I (k)=1 2 exp.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning 2βh k (T h D,I (k), δ1)2T h D,I (k)2 −T h D,I (k)(H − h + 1)2 # = HX h=1 MX m=1 X (D,I )∈T h k kX T h D,I (k)=1 2 exp

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.095384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3ce4235a-5b24-48a1-8285-89a1a0cb88e3 · outbound

This paper cites an unresolved cited work.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:55:51.213685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a7e4570c-13a3-436e-8cb7-1a27febd4ea3 · outbound

This paper cites an unresolved cited work.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:55:51.082431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e66a67d5-3b14-4c86-9a16-97175e97ba7e · outbound

This paper cites an unresolved cited work.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:55:51.067131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1bd0e7de-2af2-477b-af84-8588ec6b2317 · outbound

This paper cites an unresolved cited work.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:55:51.053984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2fff036a-ba44-4ef1-a680-33e4beec0b7e · outbound

This paper cites K · ν2 1 · 2 − ρ2 (H − h + 1)2 · ln (6M H/δ1) + 1 # + 1. (28) Through 2Dm+1 − 1, we get the upper bound of the node number of tree T h K, i.e., T h K ≤ 4.

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning K · ν2 1 · 2 − ρ2 (H − h + 1)2 · ln (6M H/δ1) + 1 # + 1. (28) Through 2Dm+1 − 1, we get the upper bound of the node number of tree T h K, i.e., T h K ≤ 4

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:55:51.039430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers