{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/create-mlp","entry":"create_mlp","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":17,"n_papers_ran":3,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":12,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":17,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"unverified":9},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2603.01771","paper":"/paper/arxiv-2603-01771","title":"Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"DLR-RM/stable-baselines3","path":"stable_baselines3/common/torch_layers.py","file_url":"https://github.com/DLR-RM/stable-baselines3/blob/HEAD/stable_baselines3/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7362fa063b732f66","mcp_get_code":{"code_sha256":"7362fa063b732f66"}},{"arxiv_id":"2602.14587","paper":"/paper/arxiv-2602-14587","title":"Decoupled Continuous-Time Reinforcement Learning via Hamiltonian Flow","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"mpnguyen2/ct-rl","path":"common/torch_layers.py","file_url":"https://github.com/mpnguyen2/ct-rl/blob/HEAD/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4e72e18159e921a7","mcp_get_code":{"code_sha256":"4e72e18159e921a7"}},{"arxiv_id":"2510.20235","paper":"/paper/arxiv-2510-20235","title":"Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"whbyeon/ERAM-ARAM","path":"stable_baselines3/common/torch_layers.py","file_url":"https://github.com/whbyeon/ERAM-ARAM/blob/HEAD/stable_baselines3/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2059f84e6efc564f","mcp_get_code":{"code_sha256":"2059f84e6efc564f"}},{"arxiv_id":"2411.19666","paper":"/paper/multimodal-whole-slide-foundation-model-for","title":"Multimodal Whole Slide Foundation Model for Pathology","date":"2024-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mahmoodlab/titan","path":"titan/finetune.py","file_url":"https://github.com/mahmoodlab/titan/blob/HEAD/titan/finetune.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ac33556a67aac0c5","mcp_get_code":{"code_sha256":"ac33556a67aac0c5"}},{"arxiv_id":"2406.16782","paper":"/paper/confidence-aware-inverse-constrained","title":"Confidence Aware Inverse Constrained Reinforcement Learning","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sriram94/confidenceawareicrl","path":"constraint_models/constraint_net/caicrl_constraint_net.py","file_url":"https://github.com/sriram94/confidenceawareicrl/blob/HEAD/constraint_models/constraint_net/caicrl_constraint_net.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2d94c0410800dae","mcp_get_code":{"code_sha256":"e2d94c0410800dae"}},{"arxiv_id":"2406.07826","paper":"/paper/the-max-min-formulation-of-multi-objective","title":"The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"giseung-park/maxmin-morl","path":"supplementary_ICML24/stable_baselines3/common/torch_layers.py","file_url":"https://github.com/giseung-park/maxmin-morl/blob/HEAD/supplementary_ICML24/stable_baselines3/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2059f84e6efc564f","mcp_get_code":{"code_sha256":"2059f84e6efc564f"}},{"arxiv_id":"2405.11643","paper":"/paper/morphological-prototyping-for-unsupervised","title":"Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology","date":"2024-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mahmoodlab/panther","path":"src/mil_models/components.py","file_url":"https://github.com/mahmoodlab/panther/blob/HEAD/src/mil_models/components.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"6a1b7452867ef4f5","mcp_get_code":{"code_sha256":"6a1b7452867ef4f5"}},{"arxiv_id":"2405.05349","paper":"/paper/offline-model-based-optimization-via-policy","title":"Offline Model-Based Optimization via Policy-Guided Gradient Search","date":"2024-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yassineCh/PGS","path":"embed.py","file_url":"https://github.com/yassineCh/PGS/blob/HEAD/embed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2b3c0c162fb9aa5b","mcp_get_code":{"code_sha256":"2b3c0c162fb9aa5b"}},{"arxiv_id":"2208.07363","paper":"/paper/mocapact-a-multi-task-dataset-for-simulated","title":"MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control","date":"2022-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/MoCapAct","path":"mocapact/sb3/torch_layers.py","file_url":"https://github.com/microsoft/MoCapAct/blob/HEAD/mocapact/sb3/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"799c901a620242f0","mcp_get_code":{"code_sha256":"799c901a620242f0"}},{"arxiv_id":"2208.03374","paper":"/paper/learning-to-generalize-with-object-centric","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","date":"2022-08-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"astanic/crafter-ood","path":"stable_baselines3/common/torch_layers.py","file_url":"https://github.com/astanic/crafter-ood/blob/HEAD/stable_baselines3/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ef103f787c48beca","mcp_get_code":{"code_sha256":"ef103f787c48beca"}},{"arxiv_id":"2205.05138","paper":"/paper/efficient-risk-averse-reinforcement-learning","title":"Efficient Risk-Averse Reinforcement Learning","date":"2022-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fictivename/cesor_ppo","path":"stable_baselines3/common/torch_layers.py","file_url":"https://github.com/fictivename/cesor_ppo/blob/HEAD/stable_baselines3/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2059f84e6efc564f","mcp_get_code":{"code_sha256":"2059f84e6efc564f"}},{"arxiv_id":"2111.11229","paper":"/paper/off-policy-correction-for-multi-agent","title":"Off-Policy Correction For Multi-Agent Reinforcement Learning","date":"2021-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"awarelab/seed_rl","path":"agents/sac/networks.py","file_url":"https://github.com/awarelab/seed_rl/blob/HEAD/agents/sac/networks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4a1477f42fca643a","mcp_get_code":{"code_sha256":"4a1477f42fca643a"}},{"arxiv_id":"2111.03941","paper":"/paper/time-discretization-invariant-safe-action","title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","date":"2021-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"artberryx/SAR","path":"sb3/stable_baselines3/common/torch_layers.py","file_url":"https://github.com/artberryx/SAR/blob/HEAD/sb3/stable_baselines3/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ef103f787c48beca","mcp_get_code":{"code_sha256":"ef103f787c48beca"}},{"arxiv_id":"2110.09192","paper":"/paper/learning-optimal-conformal-classifiers-1","title":"Learning Optimal Conformal Classifiers","date":"2021-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepmind/conformal_training","path":"models.py","file_url":"https://github.com/deepmind/conformal_training/blob/HEAD/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"78e646ce84523a39","mcp_get_code":{"code_sha256":"78e646ce84523a39"}},{"arxiv_id":"2010.14484","paper":"/paper/one-solution-is-not-all-you-need-few-shot","title":"One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL","date":"2020-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"egiob/diversityisallyouneed-sb3","path":"stable_baselines3/common/torch_layers.py","file_url":"https://github.com/egiob/diversityisallyouneed-sb3/blob/HEAD/stable_baselines3/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ef103f787c48beca","mcp_get_code":{"code_sha256":"ef103f787c48beca"}},{"arxiv_id":"2007.08728","paper":"/paper/detecting-human-object-interactions-with","title":"Detecting Human-Object Interactions with Action Co-occurrence Priors","date":"2020-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Dong-JinKim/ActionCooccurrencePriors","path":"utils/pytorch_layers.py","file_url":"https://github.com/Dong-JinKim/ActionCooccurrencePriors/blob/HEAD/utils/pytorch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"00ad97d3fa0e9432","mcp_get_code":{"code_sha256":"00ad97d3fa0e9432"}},{"arxiv_id":"1910.06591","paper":"/paper/seed-rl-scalable-and-efficient-deep-rl-with-1","title":"SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference","date":"2019-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/seed_rl","path":"agents/sac/networks.py","file_url":"https://github.com/google-research/seed_rl/blob/HEAD/agents/sac/networks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4a1477f42fca643a","mcp_get_code":{"code_sha256":"4a1477f42fca643a"}}]}