Paper Citation Record · LEDGER

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments

As of 10 August 2026, this Paper Citation Record lists 69 of 69 outbound references and 2 inbound Pith citation observations for arXiv:2603.06009.

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

pith.paper-citation-record.v1
2603.06009 v2

Coverage vector

measured 69 of 69 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T18:45:23.213117Z

measured 71 of 71 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-12T01:56:51.940356Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T08:51:25.700420Z

Reference resolution

69 of 69 outbound references displayed

verified exact1
verified fuzzy0
unresolved68
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 324d468a-0ef7-41ab-b8a8-d109b3222946 · outbound

This paper cites write newline.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.203273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16ea3926-2720-442f-ae65-02428ba04317 · outbound

This paper cites What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.216901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faf2f041-1fb4-4e78-9f94-50969c0b27b6 · outbound

This paper cites Unifying count-based exploration and intrinsic motivation.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Unifying count-based exploration and intrinsic motivation

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.229450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28fb3107-307e-41a2-8469-f286488a6e10 · outbound

This paper cites Nonlinear programming.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Nonlinear programming

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.241718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1df8c173-9bf6-4d1f-ac95-936ba5d5a96f · outbound

This paper cites Staggered environment resets improve massively parallel on-policy reinforcement learning.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Staggered environment resets improve massively parallel on-policy reinforcement learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.253010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb988d13-6dab-4f1c-b529-8a7da5239187 · outbound

This paper cites Towards deeper deep reinforcement learning with spectral normalization.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Towards deeper deep reinforcement learning with spectral normalization

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.267228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5888563a-2747-4fc3-b190-2c4515fb867d · outbound

This paper cites Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.286849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef4fe975-aabb-4c6f-92e3-5ef0f4d70094 · outbound

This paper cites Mixtures of experts unlock parameter scaling for deep RL.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Mixtures of experts unlock parameter scaling for deep RL

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.303337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7eca6dc-852f-436d-8d4b-ad834820aeea · outbound

This paper cites Two-timescale networks for nonlinear value function approximation.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Two-timescale networks for nonlinear value function approximation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.319817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1301120-9d07-4b2a-9c3e-3a6924f17330 · outbound

This paper cites Bayen, Stuart Russell, Andrew Critch, and Sergey Levine.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Bayen, Stuart Russell, Andrew Critch, and Sergey Levine

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.332979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2954065a-4892-47da-8cff-e2e127b8d2b8 · outbound

This paper cites Revisiting lars for large batch training generalization of neural networks.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Revisiting lars for large batch training generalization of neural networks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.346469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e25f19ba-1351-4903-a07a-df1185db8a76 · outbound

This paper cites First return, then explore.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments First return, then explore

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.411579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43518c25-4e3d-4773-8eda-17dedb3c887c · outbound

This paper cites Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.537597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84acd0c9-d1fa-439f-ada0-722524b2f624 · outbound

This paper cites Daniel Freeman, Erik Frey, Anton Raichuk, Sertan Girgin, Igor Mordatch, and Olivier Bachem.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Daniel Freeman, Erik Frey, Anton Raichuk, Sertan Girgin, Igor Mordatch, and Olivier Bachem

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.648056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0f8730c-77fb-48c0-ac05-e358dc8b2efb · outbound

This paper cites AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.779259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c7485fc-90ed-4c3c-8089-40ae59723b91 · outbound

This paper cites Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.901597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8e47bd5-a90c-43b4-8454-cfca8ed370d0 · outbound

This paper cites Learning rates as a function of batch size: A random matrix theory approach to neural network training.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Learning rates as a function of batch size: A random matrix theory approach to neural network training

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.987553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d6d2f4c-d71e-477b-934b-848029d12e20 · outbound

This paper cites Batch size-invariance for policy optimization.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Batch size-invariance for policy optimization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:21.086389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23e6dcbc-c46c-4c9a-bfac-ee5c337af806 · outbound

This paper cites Scaling laws for single-agent reinforcement learning.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Scaling laws for single-agent reinforcement learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:21.203626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fb6e709-9532-4297-ae33-d5c542ea6ebf · outbound

This paper cites Position: Open-endedness is essential for artificial superhuman intelligence.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Position: Open-endedness is essential for artificial superhuman intelligence

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:21.320970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dd5cc85-b604-4cb7-af86-976b18d92667 · outbound

This paper cites A Closer Look at Deep Policy Gradients.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments A Closer Look at Deep Policy Gradients

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:21.412418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cf2602e-2935-463b-bfca-1da5cd997345 · outbound

This paper cites Prioritized level replay.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Prioritized level replay

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:21.492814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ea2447c-fc09-4fd3-ab26-5eb21f0958eb · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Adam: A Method for Stochastic Optimization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:21.623678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 993ae644-4fa5-4a2f-bea7-cbd992480a14 · outbound

This paper cites One weird trick for parallelizing convolutional neural networks.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments One weird trick for parallelizing convolutional neural networks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:21.702560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92ef049f-6854-45cd-a5fb-b9f56bc40c82 · outbound

This paper cites u ttler, Nantas Nardelli, Alexander Miller, Roberta Raileanu, Marco Selvatici, Edward Grefenstette, and Tim Rockt \.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments u ttler, Nantas Nardelli, Alexander Miller, Roberta Raileanu, Marco Selvatici, Edward Grefenstette, and Tim Rockt \

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:21.850672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d44a1b1d-885f-44a0-80f2-e25c2b5b5dd8 · outbound

This paper cites gymnax : A JAX -based reinforcement learning environment library, 2022.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments gymnax : A JAX -based reinforcement learning environment library, 2022

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:21.931314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 838de2d9-fb23-4d12-b0b4-99a48bdbe22a · outbound

This paper cites Wurman, Jaegul Choo, Peter Stone, and Takuma Seno.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Wurman, Jaegul Choo, Peter Stone, and Takuma Seno

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:22.011868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f9d073a-5ea2-4f7f-a7d9-3f3f246c324d · outbound

This paper cites Hyperspherical Normalization for Scalable Deep Reinforcement Learning.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Hyperspherical Normalization for Scalable Deep Reinforcement Learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:22.126026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f861d90e-6353-42d7-87e6-c02021e58cae · outbound

This paper cites Linear and nonlinear programming, volume 2.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Linear and nonlinear programming, volume 2

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:22.251346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2b46b9e-831e-4f74-8524-fb4bc35f4966 · outbound

This paper cites Understanding and preventing capacity loss in reinforcement learning.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Understanding and preventing capacity loss in reinforcement learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:22.373975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe001b47-43e7-46af-9320-0ad2ea4bede0 · outbound

This paper cites Disentangling the causes of plasticity loss in neural networks.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Disentangling the causes of plasticity loss in neural networks

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:22.423849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe17d574-42d3-444e-ac1e-727b272e7504 · outbound

This paper cites Isaac gym: High performance GPU based physics simulation for robot learning.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Isaac gym: High performance GPU based physics simulation for robot learning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:22.489621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a551a44c-467b-461f-9d42-f1d455fc40b9 · outbound

This paper cites On the sdes and scaling rules for adaptive gradient algorithms.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments On the sdes and scaling rules for adaptive gradient algorithms

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:22.574471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c67d8891-9c09-4bc8-b702-32f708d5aaba · outbound

This paper cites Craftax: A lightning-fast benchmark for open-ended reinforcement learning.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Craftax: A lightning-fast benchmark for open-ended reinforcement learning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:22.677138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f068f8c5-a260-429a-a3cb-6ec93fe5ea20 · outbound

This paper cites Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:22.786428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de666f82-b53d-4177-8517-a5745efb7be0 · outbound

This paper cites An Empirical Model of Large-Batch Training.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments An Empirical Model of Large-Batch Training

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:22.899915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cbd09d7-fade-4eab-b894-4cf64e724026 · outbound

This paper cites Multi-task reinforcement learning enables parameter scaling.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Multi-task reinforcement learning enables parameter scaling

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:22.948817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ae9d672-186c-45b1-99fe-59c41a664d58 · outbound

This paper cites Bigger, regularized, optimistic: scaling for compute and sample efficient continuous control.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Bigger, regularized, optimistic: scaling for compute and sample efficient continuous control

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.005083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01f8fc35-d3ca-401d-a589-16f3f8687429 · outbound

This paper cites The primacy bias in deep reinforcement learning.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments The primacy bias in deep reinforcement learning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.062351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8744c93-dc41-4b3f-bdbd-866b779031bf · outbound

This paper cites XL and-minigrid: Scalable meta-reinforcement learning environments in JAX.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments XL and-minigrid: Scalable meta-reinforcement learning environments in JAX

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.094899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb04fbd9-728a-441e-80c6-3c6487dd0c41 · outbound

This paper cites XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-08-02T18:48:31.995581Z

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 25a4f697-d4df-4743-8780-96d65cf35f4a · outbound

This paper cites Numerical optimization.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Numerical optimization

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.103513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b20b069-19e4-4ba2-8f6e-040ab9f682c0 · outbound

This paper cites Training Larger Networks for Deep Reinforcement Learning.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Training Larger Networks for Deep Reinforcement Learning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.108589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc16fb24-25c5-4cc7-be89-c9b5748c58fc · outbound

This paper cites Evolving curricula with regret-based environment design.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Evolving curricula with regret-based environment design

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.113006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d7f2e7d-8748-499a-af22-96db5cc90e98 · outbound

This paper cites Some methods of speeding up the convergence of iteration methods.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Some methods of speeding up the convergence of iteration methods

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.117078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b763ee1-377f-43f5-a79f-e43d3f2b647e · outbound

This paper cites A stochastic approximation method.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments A stochastic approximation method

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.121237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec434f3f-33f7-441b-a989-de607ede3ee9 · outbound

This paper cites JaxMARL: Multi-Agent RL Environments and Algorithms in JAX.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.125183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ba84456-3169-4b8a-8839-d9cba76eae96 · outbound

This paper cites No regrets: Investigating and improving regret approximations for curriculum discovery.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments No regrets: Investigating and improving regret approximations for curriculum discovery

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.129183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5377ea3c-39fd-4430-a539-6e3b7fb450d0 · outbound

This paper cites Value-based deep RL scales predictably.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Value-based deep RL scales predictably

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.133253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8a4a067-209c-474a-ba56-eca104e763b0 · outbound

This paper cites High-Dimensional Continuous Control Using Generalized Advantage Estimation.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments High-Dimensional Continuous Control Using Generalized Advantage Estimation

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.137181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b01029d-8b70-44eb-a41b-3577843ee218 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Proximal Policy Optimization Algorithms

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.141968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16f3a565-b1f6-40be-8766-d6f0c9ed186c · outbound

This paper cites Bigger, better, faster: Human-level atari with human-level efficiency.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Bigger, better, faster: Human-level atari with human-level efficiency

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.145966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1224cad9-23c2-4029-8ef8-44a43e3a4e2c · outbound

This paper cites SAPG: Split and Aggregate Policy Gradients.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments SAPG: Split and Aggregate Policy Gradients

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.149868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abc960eb-0465-489d-9429-06cd16a32162 · outbound

This paper cites Smith, Pieter-Jan Kindermans, and Quoc V.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Smith, Pieter-Jan Kindermans, and Quoc V

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.153984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92398630-9fb0-470f-8327-f3ce3b78e661 · outbound

This paper cites Why open-endedness matters.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Why open-endedness matters

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.158003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ded6a708-c11a-47c7-a5ac-091b9e5bdee0 · outbound

This paper cites Characterization and Mitigation of Training Instabilities in Microscaling Formats.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Characterization and Mitigation of Training Instabilities in Microscaling Formats

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.162011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 276c54a0-5753-4591-b5aa-47e461ed3223 · outbound

This paper cites On Bonus-Based Exploration Methods in the Arcade Learning Environment.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments On Bonus-Based Exploration Methods in the Arcade Learning Environment

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.166185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 058f5053-c8a0-4149-a692-54718f1bd4a8 · outbound

This paper cites Beyond the Boundaries of Proximal Policy Optimization.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Beyond the Boundaries of Proximal Policy Optimization

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.170247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 438a996f-6afd-4a5e-9be5-15d374122f90 · outbound

This paper cites Human-Timescale Adaptation in an Open-Ended Task Space.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Human-Timescale Adaptation in an Open-Ended Task Space

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.174550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fb0f036-004b-491f-abaa-551f1b531280 · outbound

This paper cites Open-Ended Learning Leads to Generally Capable Agents.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Open-Ended Learning Leads to Generally Capable Agents

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.178594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68765e25-3cf7-4553-8bc6-45ea749fe06e · outbound

This paper cites Efficient exploration in reinforcement learning.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Efficient exploration in reinforcement learning

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.182591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06f0c469-6455-43a9-ab8b-b8f11ad12f5b · outbound

This paper cites Stoix: Distributed Single-Agent Reinforcement Learning End-to-End in JAX , April 2024.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Stoix: Distributed Single-Agent Reinforcement Learning End-to-End in JAX , April 2024

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.186289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1eab8c5-2e04-4362-a662-209a46724942 · outbound

This paper cites 1000 layer networks for self-supervised RL : Scaling depth can enable new goal-reaching capabilities.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments 1000 layer networks for self-supervised RL : Scaling depth can enable new goal-reaching capabilities

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.189894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a12b9ae3-56ba-47c9-97dd-068273d774d4 · outbound

This paper cites Truly proximal policy optimization.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Truly proximal policy optimization

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.193619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58b54141-451e-44eb-83bd-2b6fda085b36 · outbound

This paper cites A finite-time analysis of two time-scale actor-critic methods.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments A finite-time analysis of two time-scale actor-critic methods

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.197554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 615725cc-be96-4575-8c2d-cecc3ccf8d5a · outbound

This paper cites Kahrs, Carlo Sferrazza, Yuval Tassa, and Pieter Abbeel.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Kahrs, Carlo Sferrazza, Yuval Tassa, and Pieter Abbeel

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.201163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 719932f3-f12e-4724-8a26-baa72efd50e6 · outbound

This paper cites Fast two-time-scale stochastic gradient method with applications in reinforcement learning.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Fast two-time-scale stochastic gradient method with applications in reinforcement learning

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.205161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cccd674e-dd4a-47b1-9455-cc35bd91bd20 · outbound

This paper cites A two-time-scale stochastic optimization framework with applications in control and reinforcement learning.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments A two-time-scale stochastic optimization framework with applications in control and reinforcement learning

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.209039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97d2c54e-5a2d-460d-983a-cfc813566cd2 · outbound

This paper cites Stabilizing reinforcement learning with llms: Formulation and practices.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments Stabilizing reinforcement learning with llms: Formulation and practices

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:23.213117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 783a5005-aee6-441d-b65a-5f2230404964 · inbound

Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control cites this paper.

Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-21T01:19:54.005423Z

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 b8e32634-548b-434a-9051-726edda6527f · inbound

Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control cites this paper.

Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-21T01:19:54.005423Z

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.