Pith. sign in

REVIEW 3 major objections 2 minor 2 cited by

EVOM discovers superior actor-critic architectures by evolving programs in an outer loop with a decoupled LLM design agent.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-06-26 01:38 UTC pith:IZ5R4RWN

load-bearing objection EVOM frames RL architecture search as bi-level optimization with a fully decoupled LLM design agent, but the abstract supplies no numbers or details to back the outperformance claims on Ant-v4 and HalfCheetah-v4. the 3 major comments →

arxiv 2606.26327 v1 pith:IZ5R4RWN submitted 2026-06-24 cs.LG cs.AI

EVOM: Agentic Meta-Evolution of Actor-Critic Architectures for Reinforcement Learning

Boyun Zhang , Chao Wang , Kai Wu This is my paper
classification cs.LG cs.AI
keywords actor-criticarchitecture searchmeta-evolutionLLM agentreinforcement learningPPObi-level optimizationcontinuous control
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents EVOM as a way to automate network architecture design in actor-critic reinforcement learning, where designs are normally chosen by hand. It sets up a bi-level process: an inner loop trains candidate policies with low-fidelity PPO, while an outer loop uses an LLM agent to iteratively improve architecture programs. The agent functions solely as a designer and stays separate from policy execution or environment steps. On Ant-v4 and HalfCheetah-v4, EVOM exceeds a manual baseline, LLM-guided random search, and the prior MLES method. Ablation checks confirm that both the meta-evolution loop and the LLM agent are required to reach the reported gains.

Core claim

EVOM frames architecture search as bi-level optimization in which an inner loop trains weights via proximal policy optimization while an outer loop drives meta-evolution by iteratively refining architecture programs; the outer loop is powered by an LLM-based design agent that operates purely as an architecture designer, completely decoupled from policy execution and environment control, and the resulting architectures outperform manually designed baselines, LLM-guided random search, and the state-of-the-art LLM-guided programmatic policy search method MLES on Ant-v4 and HalfCheetah-v4.

What carries the argument

The LLM-based design agent in the outer meta-evolution loop that iteratively refines architecture programs while remaining fully decoupled from the inner PPO training loop.

Load-bearing premise

An LLM acting only as an architecture designer in the outer loop can reliably produce high-performance actor-critic programs without any coupling to policy execution or environment control.

What would settle it

Running EVOM on additional continuous-control environments beyond Ant-v4 and HalfCheetah-v4 and observing that the discovered architectures no longer outperform the manual baseline or MLES would falsify the superiority claim.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Architecture search in actor-critic RL can be automated without manual intervention or full coupling of design to training.
  • Both the meta-evolution loop and the LLM design agent contribute indispensably to the performance gains.
  • The approach handles an open-ended design space by evolving programs rather than enumerating fixed candidates.
  • Low-fidelity PPO in the inner loop is sufficient to guide the outer evolution toward high-performing final architectures.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same decoupled outer-loop structure could be tested on other reinforcement-learning families such as value-based or model-based methods.
  • If the LLM agent remains effective when the inner loop uses even cheaper proxies, the method might scale to larger or more expensive environments.
  • The separation of design from execution raises the question of whether similar agentic loops could automate other open-ended design tasks in machine learning.
  • Repeating the search multiple times and checking consistency of the discovered architectures would test whether the meta-evolution produces stable, reproducible results.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

3 major / 2 minor

Summary. The paper introduces EVOM, a bi-level optimization framework for automating actor-critic architecture design in RL. An inner loop trains network weights with low-fidelity PPO; an outer loop performs meta-evolution of architecture programs via an LLM-based design agent that is fully decoupled from policy execution and environment interaction. The central empirical claim is that EVOM outperforms a manually designed baseline, LLM-guided random search, and the SOTA method MLES on Ant-v4 and HalfCheetah-v4, with ablations confirming that both the meta-evolution loop and the LLM agent are required for the reported gains.

Significance. If the experimental results are robust, the work would demonstrate a viable path for LLM-driven architecture search in RL that avoids direct environment coupling, potentially reducing the cost of manual design while still achieving measurable gains over strong baselines. The separation of the design agent from execution is a distinctive design choice that, if shown to work, would be of interest to the AutoML and RL communities.

major comments (3)
  1. [Abstract / §1] The abstract and §1 claim outperformance on Ant-v4 and HalfCheetah-v4, yet no quantitative results, number of independent runs, statistical tests, or variance measures are supplied in the provided text. Without these, it is impossible to determine whether the reported superiority is statistically reliable or practically meaningful.
  2. [Abstract / §3] The description of the outer-loop LLM design agent (abstract and §3) states that it operates 'completely decoupled from policy execution and environment control' and receives only 'indirect textual summaries.' For the central claim to hold, the paper must show that this feedback mechanism enables iterative improvement beyond the LLM's pretrained priors; the current text provides no prompt templates, summary format, or example trajectories that would allow verification of adaptive, data-driven refinement.
  3. [Abstract / Experiments section] Ablation studies are cited as validating the necessity of both the meta-evolution loop and the LLM Design Agent, but no details are given on the ablation conditions (e.g., what replaces the LLM, how many architectures are evaluated, or the resulting performance deltas). These ablations are load-bearing for the claim that the proposed components are indispensable.
minor comments (2)
  1. [§2 / §3] Notation for the bi-level optimization and the architecture program representation should be introduced with explicit equations or pseudocode early in the methods section.
  2. [Related Work] The relationship between EVOM and prior LLM-guided search methods (including MLES) should include a clearer tabular comparison of key differences in feedback, search space, and decoupling.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive comments. We address each major point below and will revise the manuscript accordingly to improve clarity and completeness.

read point-by-point responses

  1. Referee: [Abstract / §1] The abstract and §1 claim outperformance on Ant-v4 and HalfCheetah-v4, yet no quantitative results, number of independent runs, statistical tests, or variance measures are supplied in the provided text. Without these, it is impossible to determine whether the reported superiority is statistically reliable or practically meaningful.

    Authors: We agree that the abstract and §1 should include key quantitative results for transparency. The experiments section contains tables with mean returns, standard deviations across 5-10 seeds, and comparisons, but these were not summarized in the abstract or introduction. We will revise both sections to report specific metrics (e.g., final returns with variance) and note the statistical reliability of the gains. revision: yes

  2. Referee: [Abstract / §3] The description of the outer-loop LLM design agent (abstract and §3) states that it operates 'completely decoupled from policy execution and environment control' and receives only 'indirect textual summaries.' For the central claim to hold, the paper must show that this feedback mechanism enables iterative improvement beyond the LLM's pretrained priors; the current text provides no prompt templates, summary format, or example trajectories that would allow verification of adaptive, data-driven refinement.

    Authors: We acknowledge that explicit prompt templates, summary formats, and example trajectories are needed to demonstrate adaptive refinement. The current manuscript describes the mechanism at a high level but omits these details. We will add them to an expanded §3 and/or appendix, including sample prompts and trajectories illustrating how textual feedback drives architecture changes beyond initial priors. revision: yes

  3. Referee: [Abstract / Experiments section] Ablation studies are cited as validating the necessity of both the meta-evolution loop and the LLM Design Agent, but no details are given on the ablation conditions (e.g., what replaces the LLM, how many architectures are evaluated, or the resulting performance deltas). These ablations are load-bearing for the claim that the proposed components are indispensable.

    Authors: We agree that the ablation details are insufficient as presented. The manuscript references the ablations but does not specify the replacement conditions (e.g., random search or non-LLM variants), evaluation counts, or exact deltas. We will expand the experiments section with these specifics, including tables showing performance differences to substantiate the necessity of each component. revision: yes

Circularity Check

0 steps flagged

No circularity in empirical architecture search framework

full rationale

The paper describes an empirical bi-level optimization procedure (inner PPO training, outer LLM-driven architecture refinement) whose central claims consist of measured outperformance on Ant-v4 and HalfCheetah-v4 against explicit baselines. No equations, predictions, or uniqueness theorems are presented that reduce by construction to fitted inputs, self-citations, or renamed ansatzes; the reported results are obtained from external environment rollouts and are therefore falsifiable independently of the method description itself.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review supplies no explicit free parameters, axioms, or invented entities.

pith-pipeline@v0.9.1-grok · 5709 in / 1023 out tokens · 23089 ms · 2026-06-26T01:38:06.243880+00:00 · methodology

0 comments
read the original abstract

In actor-critic reinforcement learning, network architectures are typically manually designed. Automating this design is challenging because each candidate must be trained before evaluation, and the design space is open-ended. To address these challenges, we introduce EVOM, an agentic meta-evolution framework for discovering high-performance actor-critic architectures. We frame architecture search as a bi-level optimization: an inner loop trains weights via the low-fidelity proximal policy optimization (PPO), while an outer loop drives meta-evolution by iteratively refining architecture programs. Crucially, this outer loop is powered by an LLM-based design agent that operates purely as an architecture designer, completely decoupled from policy execution and environment control. Experiments reveal that EVOM outperforms the manually designed baseline, an LLM-guided random search, and the state-of-the-art LLM-guided programmatic policy search method MLES, delivering superior performance on Ant-v4 and HalfCheetah-v4. Ablation studies validate that both the meta-evolution loop and the LLM Design Agent are indispensable for final performance.

Figures

Figures reproduced from arXiv: 2606.26327 by Boyun Zhang, Chao Wang, Kai Wu.

Figure 1
Figure 1. Figure 1: Overview of EVOM as bi-level optimization: Outer loop evolves architectures, and inner loop trains weights. [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Prompt templates for initialization, mutation, and [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Main experimental results on Ant-v4. The evolution loop improves the historical-best reward and the elite-population mean. The [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Main experimental results on HalfCheetah-v4. The final selected actor-critic architecture uses a deeper LayerNorm-SiLU MLP [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops

    cs.AI 2026-07 conditional novelty 6.0

    A survey of 1,250 papers organizes AI self-improvement along two axes—what is improved and loop closure—finding that demonstrated self-improvement strength tracks a verification hierarchy from formal verifiers down to...

  2. Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems

    cs.NE 2026-07 accept novelty 5.0

    Evolutionary intelligence reframes evolutionary computation as cumulative scientific discovery by retaining search trajectories, failures, and lineages across cycles.

Reference graph

Works this paper leans on

35 extracted references · 5 canonical work pages · cited by 2 Pith papers · 5 internal anchors

  1. [1]

    Oxford University Press,

    [B¨ack, 1996] Thomas B ¨ack.Evolutionary Algorithms in Theory and Practice. Oxford University Press,

    1996

  2. [2]

    OpenAI Gym

    [Brockmanet al., 2016 ] Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. Openai gym.arXiv preprint arXiv:1606.01540,

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  3. [3]

    [Brownet al., 2020 ] Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhari- wal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-V oss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Win- ter, Christopher Hesse, Mark Chen, E...

    2020

  4. [4]

    Evaluating Large Language Models Trained on Code

    [Chenet al., 2021 ] Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. Evaluating large language models trained on code.arXiv preprint arXiv:2107.03374,

    work page internal anchor Pith review Pith/arXiv arXiv 2021

  5. [5]

    Neural architecture search: A sur- vey.Journal of Machine Learning Research, 20(55):1–21,

    [Elskenet al., 2019 ] Thomas Elsken, Jan Hendrik Metzen, and Frank Hutter. Neural architecture search: A sur- vey.Journal of Machine Learning Research, 20(55):1–21,

    2019

  6. [6]

    Weight ag- nostic neural networks

    [Gaier and Ha, 2019] Adam Gaier and David Ha. Weight ag- nostic neural networks. InAdvances in Neural Information Processing Systems,

    2019

  7. [7]

    [Grondmanet al., 2012 ] Ivo Grondman, Lucian Busoniu, Gabriel AD Lopes, and Robert Babuska. A survey of actor-critic reinforcement learning: Standard and natu- ral policy gradients.IEEE Transactions on Systems, Man, and Cybernetics, part C (applications and reviews), 42(6):1291–1307,

    2012

  8. [8]

    Mul- timodal LLM-assisted evolutionary search for program- matic control policies

    [Huet al., 2026 ] Qinglong Hu, Tong Xialiang, Mingxuan Yuan, Fei Liu, Zhichao Lu, and Qingfu Zhang. Mul- timodal LLM-assisted evolutionary search for program- matic control policies. InThe Fourteenth International Conference on Learning Representations,

    2026

  9. [9]

    Koza.Genetic Programming: On the Programming of Computers by Means of Natural Selec- tion

    [Koza, 1992] John R. Koza.Genetic Programming: On the Programming of Computers by Means of Natural Selec- tion. MIT Press,

    1992

  10. [10]

    Deep learning.nature, 521(7553):436–444,

    [LeCunet al., 2015 ] Yann LeCun, Yoshua Bengio, and Ge- offrey Hinton. Deep learning.nature, 521(7553):436–444,

    2015

  11. [11]

    Bridging evolutionary algo- rithms and reinforcement learning: A comprehensive sur- vey on hybrid algorithms.IEEE Transactions on evolu- tionary computation,

    [Liet al., 2024 ] Pengyi Li, Jianye Hao, Hongyao Tang, Xian Fu, Yan Zhen, and Ke Tang. Bridging evolutionary algo- rithms and reinforcement learning: A comprehensive sur- vey on hybrid algorithms.IEEE Transactions on evolu- tionary computation,

    2024

  12. [12]

    A survey on evolutionary neural architecture search.IEEE transac- tions on neural networks and learning systems, 34(2):550– 570,

    [Liuet al., 2021 ] Yuqiao Liu, Yanan Sun, Bing Xue, Mengjie Zhang, Gary G Yen, and Kay Chen Tan. A survey on evolutionary neural architecture search.IEEE transac- tions on neural networks and learning systems, 34(2):550– 570,

    2021

  13. [13]

    Evolution of heuristics: Towards efficient auto- matic algorithm design using large language model

    [Liuet al., 2024 ] Fei Liu, Tong Xialiang, Mingxuan Yuan, Xi Lin, Fu Luo, Zhenkun Wang, Zhichao Lu, and Qingfu Zhang. Evolution of heuristics: Towards efficient auto- matic algorithm design using large language model. In Forty-first International Conference on Machine Learning,

    2024

  14. [14]

    A systematic survey on large language models for algorithm design.ACM Comput

    [Liuet al., 2026 ] Fei Liu, Yiming Yao, Ping Guo, Zhiyuan Yang, Xi Lin, Zhe Zhao, Xialiang Tong, Kun Mao, Zhichao Lu, Zhenkun Wang, Mingxuan Yuan, and Qingfu Zhang. A systematic survey on large language models for algorithm design.ACM Comput. Surv., 58(8), February

    2026

  15. [15]

    Eureka: Human-level reward design via coding large language models

    [Maet al., 2024 ] Yecheng Jason Ma, William Liang, Guanzhi Wang, De-An Huang, Osbert Bastani, Dinesh Jayaraman, Yuke Zhu, Linxi Fan, and Anima Anand- kumar. Eureka: Human-level reward design via coding large language models. InInternational Conference on Learning Representations,

    2024

  16. [16]

    Toward automated al- gorithm design: A survey and practical guide to meta- black-box-optimization.IEEE Transactions on Evolution- ary Computation, 30(2):667–687,

    [Maet al., 2026 ] Zeyuan Ma, Hongshu Guo, Yue-Jiao Gong, Jun Zhang, and Kay Chen Tan. Toward automated al- gorithm design: A survey and practical guide to meta- black-box-optimization.IEEE Transactions on Evolution- ary Computation, 30(2):667–687,

    2026

  17. [17]

    Self-refine: Iterative refinement with self- feedback.Advances in neural information processing sys- tems, 36:46534–46594,

    [Madaanet al., 2023 ] Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, et al. Self-refine: Iterative refinement with self- feedback.Advances in neural information processing sys- tems, 36:46534–46594,

    2023

  18. [18]

    Neuroevolution insights into biological neural computation.Science, 387(6735):eadp7478,

    [Miikkulainen, 2025] Risto Miikkulainen. Neuroevolution insights into biological neural computation.Science, 387(6735):eadp7478,

    2025

  19. [19]

    Gpt-4 technical report

    [OpenAI, 2023] OpenAI. Gpt-4 technical report. Technical report, OpenAI,

    2023

  20. [20]

    Training lan- guage models to follow instructions with human feedback

    [Ouyanget al., 2022 ] Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. Training lan- guage models to follow instructi...

    2022

  21. [21]

    Stable-baselines3: Reliable reinforcement learning implementations.Journal of Machine Learning Research, 22(268):1–8,

    [Raffinet al., 2021 ] Antonin Raffin, Ashley Hill, Adam Gleave, Anssi Kanervisto, Maximilian Ernestus, and Noah Dormann. Stable-baselines3: Reliable reinforcement learning implementations.Journal of Machine Learning Research, 22(268):1–8,

    2021

  22. [22]

    [Realet al., 2019 ] Esteban Real, Alok Aggarwal, Yanping Huang, and Quoc V . Le. Regularized evolution for image classifier architecture search. InProceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 4780–4789,

    2019

  23. [23]

    Mathematical discoveries from program search with large language models.Nature, 625(7995):468–475,

    [Romera-Paredeset al., 2024 ] Bernardino Romera-Paredes, Mohammadamin Barekatain, Alexander Novikov, Matej Balog, M Pawan Kumar, Emilien Dupont, Francisco JR Ruiz, Jordan S Ellenberg, Pengming Wang, Omar Fawzi, et al. Mathematical discoveries from program search with large language models.Nature, 625(7995):468–475,

    2024

  24. [24]

    Evolution Strategies as a Scalable Alternative to Reinforcement Learning

    [Salimanset al., 2017 ] Tim Salimans, Jonathan Ho, Xi Chen, Szymon Sidor, and Ilya Sutskever. Evolution strategies as a scalable alternative to reinforcement learning.arXiv preprint arXiv:1703.03864,

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  25. [25]

    Proximal Policy Optimization Algorithms

    [Schulmanet al., 2017 ] John Schulman, Filip Wolski, Pra- fulla Dhariwal, Alec Radford, and Oleg Klimov. Prox- imal policy optimization algorithms.arXiv preprint arXiv:1707.06347,

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  26. [26]

    Reflex- ion: Language agents with verbal reinforcement learning

    [Shinnet al., 2023 ] Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. Reflex- ion: Language agents with verbal reinforcement learning. InAdvances in Neural Information Processing Systems,

    2023

  27. [27]

    Stanley and Risto Miikkulainen

    [Stanley and Miikkulainen, 2002] Kenneth O. Stanley and Risto Miikkulainen. Evolving neural networks through augmenting topologies.Evolutionary Computation, 10(2):99–127,

    2002

  28. [28]

    Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning

    [Suchet al., 2017 ] Felipe Petroski Such, Vashisht Madha- van, Edoardo Conti, Joel Lehman, Kenneth O Stanley, and Jeff Clune. Deep neuroevolution: Genetic algo- rithms are a competitive alternative for training deep neu- ral networks for reinforcement learning.arXiv preprint arXiv:1712.06567,

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  29. [29]

    MIT press Cambridge,

    [Suttonet al., 1998 ] Richard S Sutton, Andrew G Barto, et al.Reinforcement learning: An introduction. MIT press Cambridge,

    1998

  30. [30]

    [Towerset al., 2025 ] Mark Towers, Ariel Kwiatkowski, John U. Balis, Gianluca De Cola, Tristan Deleu, Manuel Goul˜ao, Kallinteris Andreas, Markus Krimmel, Arjun KG, Rodrigo De Lazcano Perez-Vicente, J K Terry, Andrea Pierr´e, Sander V Schulhoff, Jun Jet Tai, Hannah Tan, and Omar G. Younis. Gymnasium: A standard interface for reinforcement learning environ...

    2025

  31. [31]

    V oyager: An open-ended embodied agent with large language models.Transactions on Ma- chine Learning Research,

    [Wanget al., 2024 ] Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. V oyager: An open-ended embodied agent with large language models.Transactions on Ma- chine Learning Research,

    2024

  32. [32]

    When large language models meet evolutionary algorithms: Potential enhancements and challenges.Research, 8:0646,

    [Wanget al., 2025 ] Chao Wang, Jiaxuan Zhao, Licheng Jiao, Lingling Li, Fang Liu, and Shuyuan Yang. When large language models meet evolutionary algorithms: Potential enhancements and challenges.Research, 8:0646,

    2025

  33. [33]

    React: Synergizing reasoning and acting in language mod- els

    [Yaoet al., 2023 ] Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. React: Synergizing reasoning and acting in language mod- els. InInternational Conference on Learning Representa- tions,

    2023

  34. [34]

    Using large language models for hyperparameter optimization

    [Zhanget al., 2023 ] Michael Zhang, Nishkrit Desai, Juhan Bae, Jonathan Lorraine, and Jimmy Ba. Using large language models for hyperparameter optimization. In NeurIPS 2023 Foundation Models for Decision Making Workshop,

    2023

  35. [35]

    [Zoph and Le, 2017] Barret Zoph and Quoc V . Le. Neural architecture search with reinforcement learning. InInter- national Conference on Learning Representations, 2017

    2017