Home › Code › layer_init

layer_init

Syntologyentry name in harvested coderead from the graph 2026-09-24

layer_init appears in the code Syntology harvested for 46 papers, as 20 distinct code bodies found in 51 places (a place is one code body under one paper). At least one of them ran in 38 of the papers; 0 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named layer_init do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 12 of the 20 distinct code bodies named layer_init; 8 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
7ran · our draft was wrong
0ran · fixture could not drive it
5ran
8unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 27 of the 51 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

46 papers shown of 46, newest first; 51 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 5 papers added by Syntology; 4 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
DeCoR: Design and Control Co-Optimization for Urban Streets Using Reinforcement Learning added by Syntology 2026-05 (from id) poudel-bibek/DeCoR/ppo/models.py d90a784ee56240f3 ran MIT (permissive)
Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning added by Syntology 2026-03 (from id) datake/FAME/Atari/models/dino_simple.py beb42d440ccf2925 ran · our draft was wrong no licence file found · pointer only
Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning added by Syntology 2026-03 (from id) datake/FAME/Atari/models/FastMeta.py e01d3118f70d5b05 ran · our draft was wrong no licence file found · pointer only
Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning added by Syntology 2026-03 (from id) datake/FAME/Atari/models/progressive_net.py cd674ceafb2bb134 unverified no licence file found · pointer only
Small Reward Models via Backward Inference added by Syntology 2026-02 (from id) yikee/FLIP/open-instruct/open_instruct/reward_modeling.py 85c132fb4ad771ab unverified no licence file found · pointer only
RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning added by Syntology 2026-01 (from id) alwaysbyx/RND-RL/rnd.py f507fed062498260 unverified no licence file found · pointer only
Language-based Trial and Error Falls Behind in the Era of Experience added by Syntology 29 Jan 2026 identical code first harvested elsewhere beb42d440ccf2925 ran · our draft was wrong licence of this copy not recorded
Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood 10 Jun 2025 yqpqry/sqog/SQOG.py 47c37c5b075bacaf ran · our draft was wrong no licence file found · pointer only
arXiv:2504.06386 2025-04 (from id) JacquesCloete/sport/src/sport/rl/algos/projected_ppo/core.py ad8ba118b16e67f2 ran · our draft was wrong MIT (permissive)
Handling Delay in Real-Time Reinforcement Learning 30 Mar 2025 identical code first harvested elsewhere e01d3118f70d5b05 ran · our draft was wrong licence of this copy not recorded
From Demonstrations to Rewards: Alignment Without Explicit Human Preferences 15 Mar 2025 Hong-Lab-UMN-ECE/IRLAlignment/visualize_tokens.py 9ad5922df265477f ran · our draft was wrong MIT (permissive)
Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning 14 Feb 2025 CognitiveAISystems/MIKASA-Robo/mikasa_robo_suite/rl/dataset_collectors/get_dataset_collectors_ckpt.py beb42d440ccf2925 ran · our draft was wrong MIT (permissive)
Reevaluating Policy Gradient Methods for Imperfect-Information Games 13 Feb 2025 identical code first harvested elsewhere beb42d440ccf2925 ran · our draft was wrong licence of this copy not recorded
Reevaluating Policy Gradient Methods for Imperfect-Information Games 13 Feb 2025 identical code first harvested elsewhere e01d3118f70d5b05 ran · our draft was wrong licence of this copy not recorded
Offline Behavior Distillation 30 Oct 2024 leaveslei/obd/data_lib/syndset.py f297771ebb6401b8 unverified no licence file found · pointer only
End-to-end Training for Recommendation with Language-based User Profiles 24 Oct 2024 zhaolingao/langptune/src/langptune_gemma.py 9ad5922df265477f ran · our draft was wrong MIT (permissive)
Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale 13 Oct 2024 anndvision/vsop-3d/vsop_3d/vsop_3d_procgen.py d3b66680bcde8d15 ran · our draft was wrong MIT (permissive)
Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient 11 Oct 2024 realwenlongwang/Drama/tools.py 3efc0819c7bc75e2 ran no licence file found · pointer only
Craftium: An Extensible Framework for Creating Reinforcement Learning Environments 4 Jul 2024 mikelma/craftium/cleanrl_ppo_lstm_train.py beb42d440ccf2925 ran · our draft was wrong no licence file found · pointer only
Variational Delayed Policy Optimization 23 May 2024 QingyuanWuNothing/VDPO/nn.py beb42d440ccf2925 ran · our draft was wrong no licence file found · pointer only
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO 1 May 2024 claire-labo/no-representation-no-trust/src/cleanrl/ppo_atari_original.py beb42d440ccf2925 ran · our draft was wrong MIT (permissive)
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO 1 May 2024 claire-labo/no-representation-no-trust/src/cleanrl/ppo_atari_1model.py 064fcfc6277bdc44 ran MIT (permissive)
REBEL: Reinforcement Learning via Regressing Relative Rewards 25 Apr 2024 zhaolingao/rebel/src/tldr/rebel.py 9ad5922df265477f ran · our draft was wrong Apache-2.0 (permissive)
Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning 16 Apr 2024 panxulab/MARL-CoopTS/components/network.py 3a9ab37bf0498c42 ran MIT (permissive)
Dataset Reset Policy Optimization for RLHF 12 Apr 2024 identical code first harvested elsewhere 9ad5922df265477f ran · our draft was wrong licence of this copy not recorded
Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection 10 Apr 2024 linasnas/dexter/src/train_test_detector_discrete_env.py 244a24e0c333afbe ran · our draft was wrong no licence file found · pointer only
The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization 24 Mar 2024 vwxyzjn/summarize_from_feedback_details/summarize_from_feedback_details/ppo.py 9ad5922df265477f ran · our draft was wrong MIT (permissive)
Averaging $n$-step Returns Reduces Variance in Reinforcement Learning 6 Feb 2024 brett-daley/averaging-nstep-returns/run_ppo.py beb42d440ccf2925 ran · our draft was wrong MIT (permissive)
Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays 5 Feb 2024 QingyuanWuNothing/AD-RL/nn.py beb42d440ccf2925 ran · our draft was wrong no licence file found · pointer only
True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning 25 Jan 2024 weihaotan/twosome/twosome/overcooked/ppo_llm_pomdp.py beb42d440ccf2925 ran · our draft was wrong no licence file found · pointer only
True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning 25 Jan 2024 weihaotan/twosome/twosome/overcooked/policy_pomdp.py e01d3118f70d5b05 ran · our draft was wrong no licence file found · pointer only
Learning to Act without Actions 17 Dec 2023 schmidtdominik/LAPO/lapo/models.py 79a9507515948442 unverified no licence file found · pointer only
Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks 26 Oct 2023 RyanNavillus/PPO-v3/ppo_v3/ppo_atari_envpool_resnet.py beb42d440ccf2925 ran · our draft was wrong Apache-2.0 (permissive)
Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control 26 Sep 2023 nathanrahn/return-landscapes/run_algorithm/experiments/ppo_atari_envpool.py beb42d440ccf2925 ran · our draft was wrong no licence file found · pointer only
Learning to Identify Critical States for Reinforcement Learning from Videos 15 Aug 2023 ai-initiative-kaust/videorlcs/Policy_Improvement/Atari/atari_network.py 372e9511cee496ef ran no licence file found · pointer only
Learning Diverse Risk Preferences in Population-based Self-play 19 May 2023 identical code first harvested elsewhere beb42d440ccf2925 ran · our draft was wrong licence of this copy not recorded
MCTS-GEB: Monte Carlo Tree Search is a Good E-graph Builder 8 Mar 2023 ucamrl/eqs/omelette-original/rejoice/networks.py e01d3118f70d5b05 ran · our draft was wrong MIT (permissive)
Robust Policy Optimization in Deep Reinforcement Learning 14 Dec 2022 identical code first harvested elsewhere beb42d440ccf2925 ran · our draft was wrong licence of this copy not recorded
Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning 4 Oct 2022 jaggbow/saf/src/policies/saf.py beb42d440ccf2925 ran · our draft was wrong no licence file found · pointer only
EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine 21 Jun 2022 vwxyzjn/envpool-cleanrl/ppo_atari_envpool.py beb42d440ccf2925 ran · our draft was wrong MIT (permissive)
CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms 16 Nov 2021 identical code first harvested elsewhere beb42d440ccf2925 ran · our draft was wrong licence of this copy not recorded
Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch 4 Nov 2021 ShangtongZhang/DeepRL/deep_rl/network/network_utils.py e47770c24cec6408 unverified MIT (permissive)
Randomized Exploration for Reinforcement Learning with General Value Function Approximation 15 Jun 2021 qlan3/Explorer/components/network.py 3a9ab37bf0498c42 ran MIT (permissive)
Reinforcement Learning with Convex Constraints 21 Jun 2019 xkianteb/ApproPO/ApproPO/nets.py e47770c24cec6408 unverified MIT (permissive)
Meta-Gradient Reinforcement Learning 24 May 2018 RobvanGastel/meta-rl-algorithms/utils/misc.py e12d84ba1f73ff01 unverified MIT (permissive)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks 9 Mar 2017 Octavio-Pappalardo/MAML_for_RL_pytorch/FO-MAML_distributed/network.py e01d3118f70d5b05 ran · our draft was wrong MIT (permissive)
Learning to reinforcement learn 17 Nov 2016 identical code first harvested elsewhere e01d3118f70d5b05 ran · our draft was wrong licence of this copy not recorded
RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning 9 Nov 2016 Octavio-Pappalardo/RL2-implementation-pytorch/agent_and_tbpttPPO.py e01d3118f70d5b05 ran · our draft was wrong MIT (permissive)
arXiv:openreview_KBt9iIfQAi yanmluk/causal-xrl/cxrl_microRTS/lib/gym_microrts_rl/env_tools.py e01d3118f70d5b05 ran · our draft was wrong MIT (permissive)
arXiv:aaai_29188 Jackory/RPBT/toyexample/rppo.py beb42d440ccf2925 ran · our draft was wrong MIT (permissive)
arXiv:2024.acl-long.729 xjw-nlp/SimCAS/modeling_bart_ours.py 3cd6d9bbebd8f0fe unverified Apache-2.0 (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections