{"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/linear-schedule","entry":"linear_schedule","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":26,"n_papers_ran":15,"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":18,"n_samples_ran":9,"n_samples_fingerprinted":5,"n_places":26,"n_places_pointer_only":10,"by_status":{"ran_honours":6,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"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":"2609.13044","paper":"/paper/arxiv-2609-13044","title":"Robust Policy Optimization via Adversarial Importance Sampling","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"AmineAndam04/advrl","path":"advrl/utils/nets.py","file_url":"https://github.com/AmineAndam04/advrl/blob/HEAD/advrl/utils/nets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a8c11ad133a716b4","mcp_get_code":{"code_sha256":"a8c11ad133a716b4"}},{"arxiv_id":"2510.18828","paper":"/paper/arxiv-2510-18828","title":"Actor-Free Continuous Control via Structurally Maximizable Q-Functions","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"USC-Lira/Q3C","path":"q3c/utils/learning_rate_schedulers.py","file_url":"https://github.com/USC-Lira/Q3C/blob/HEAD/q3c/utils/learning_rate_schedulers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6be8838e3058ad9c","mcp_get_code":{"code_sha256":"6be8838e3058ad9c"}},{"arxiv_id":"2508.20294","paper":"/paper/arxiv-2508-20294","title":"Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"frankroeder/DALI","path":"contextual_mbrl/baseline/model.py","file_url":"https://github.com/frankroeder/DALI/blob/HEAD/contextual_mbrl/baseline/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2df73e2474aca4ca","mcp_get_code":{"code_sha256":"2df73e2474aca4ca"}},{"arxiv_id":"2507.09391","paper":null,"title":"arXiv:2507.09391","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"peterpaohuang/ncgn","path":"src/schedules.py","file_url":"https://github.com/peterpaohuang/ncgn/blob/HEAD/src/schedules.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9929f56bc45fb62a","mcp_get_code":{"code_sha256":"9929f56bc45fb62a"}},{"arxiv_id":"2501.02087","paper":"/paper/beyond-cvar-leveraging-static-spectral-risk","title":"Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning","date":"2025-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"4c60d8998b722013","mcp_get_code":{"code_sha256":"4c60d8998b722013"}},{"arxiv_id":"2410.22388","paper":"/paper/et-flow-equivariant-flow-matching-for","title":"ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generation","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shenoynikhil/ETFlow","path":"etflow/models/utils.py","file_url":"https://github.com/shenoynikhil/ETFlow/blob/HEAD/etflow/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"21f5c6553e54587f","mcp_get_code":{"code_sha256":"21f5c6553e54587f"}},{"arxiv_id":"2410.14606","paper":"/paper/streaming-deep-reinforcement-learning-finally","title":"Streaming Deep Reinforcement Learning Finally Works","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mohmdelsayed/streaming-drl","path":"stream_q.py","file_url":"https://github.com/mohmdelsayed/streaming-drl/blob/HEAD/stream_q.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4c60d8998b722013","mcp_get_code":{"code_sha256":"4c60d8998b722013"}},{"arxiv_id":"2407.05789","paper":"/paper/candid-dac-leveraging-coupled-action","title":"CANDID DAC: Leveraging Coupled Action Dimensions with Importance Differences in DAC","date":"2024-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"philippbordne/candiddac","path":"src/candid_dac/utils/utils.py","file_url":"https://github.com/philippbordne/candiddac/blob/HEAD/src/candid_dac/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3b4e136849a4251a","mcp_get_code":{"code_sha256":"3b4e136849a4251a"}},{"arxiv_id":"2403.10967","paper":"/paper/dreaming-of-many-worlds-learning-contextual","title":"Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization","date":"2024-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sai-prasanna/dreaming_of_many_worlds","path":"contextual_mbrl/baseline/model.py","file_url":"https://github.com/sai-prasanna/dreaming_of_many_worlds/blob/HEAD/contextual_mbrl/baseline/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2df73e2474aca4ca","mcp_get_code":{"code_sha256":"2df73e2474aca4ca"}},{"arxiv_id":"2312.06348","paper":"/paper/diffail-diffusion-adversarial-imitation","title":"DiffAIL: Diffusion Adversarial Imitation Learning","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-group-sdu/diffail","path":"rlkit/core/train_util.py","file_url":"https://github.com/ml-group-sdu/diffail/blob/HEAD/rlkit/core/train_util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6287f9aeab092560","mcp_get_code":{"code_sha256":"6287f9aeab092560"}},{"arxiv_id":"2310.16828","paper":"/paper/td-mpc2-scalable-robust-world-models-for","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","date":"2023-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicklashansen/tdmpc","path":"src/algorithm/tdmpc.py","file_url":"https://github.com/nicklashansen/tdmpc/blob/HEAD/src/algorithm/tdmpc.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2a9a459391fd3de7","mcp_get_code":{"code_sha256":"2a9a459391fd3de7"}},{"arxiv_id":"2309.16984","paper":"/paper/consistency-models-as-a-rich-and-efficient","title":"Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"4c60d8998b722013","mcp_get_code":{"code_sha256":"4c60d8998b722013"}},{"arxiv_id":"2306.00975","paper":"/paper/active-vision-reinforcement-learning-under","title":"Active Vision Reinforcement Learning under Limited Visual Observability","date":"2023-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"elicassion/sugarl","path":"agent/dqn_atari_sugarl.py","file_url":"https://github.com/elicassion/sugarl/blob/HEAD/agent/dqn_atari_sugarl.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4c60d8998b722013","mcp_get_code":{"code_sha256":"4c60d8998b722013"}},{"arxiv_id":"2303.08888","paper":"/paper/stochastic-segmentation-with-conditional","title":"Stochastic Segmentation with Conditional Categorical Diffusion Models","date":"2023-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"larsdoorenbos/ccdm-stochastic-segmentation","path":"ddpm/models/diffusion_denoising.py","file_url":"https://github.com/larsdoorenbos/ccdm-stochastic-segmentation/blob/HEAD/ddpm/models/diffusion_denoising.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0bbe78920342bfbb","mcp_get_code":{"code_sha256":"0bbe78920342bfbb"}},{"arxiv_id":"2210.10195","paper":"/paper/curriculum-reinforcement-learning-using","title":"Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation","date":"2022-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"peidehuang/gradient","path":"helpers/utils.py","file_url":"https://github.com/peidehuang/gradient/blob/HEAD/helpers/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d7285fe24c34a81","mcp_get_code":{"code_sha256":"7d7285fe24c34a81"}},{"arxiv_id":"2112.03636","paper":"/paper/godot-reinforcement-learning-agents","title":"Godot Reinforcement Learning Agents","date":"2021-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"4cee71b4d9b5a737","mcp_get_code":{"code_sha256":"4cee71b4d9b5a737"}},{"arxiv_id":"2111.08819","paper":"/paper/cleanrl-high-quality-single-file","title":"CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms","date":"2021-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"4c60d8998b722013","mcp_get_code":{"code_sha256":"4c60d8998b722013"}},{"arxiv_id":"2111.03026","paper":"/paper/b-pref-benchmarking-preference-based","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","date":"2021-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rll-research/B-Pref","path":"train_PPO.py","file_url":"https://github.com/rll-research/B-Pref/blob/HEAD/train_PPO.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ad4e19d5ac571c31","mcp_get_code":{"code_sha256":"ad4e19d5ac571c31"}},{"arxiv_id":"2106.05091","paper":"/paper/pebble-feedback-efficient-interactive","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","date":"2021-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rll-research/bpref","path":"train_PPO.py","file_url":"https://github.com/rll-research/bpref/blob/HEAD/train_PPO.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ad4e19d5ac571c31","mcp_get_code":{"code_sha256":"ad4e19d5ac571c31"}},{"arxiv_id":"2105.09452","paper":"/paper/minimum-delay-adaptation-in-non-stationary","title":"Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection","date":"2021-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LucasAlegre/mbcd","path":"mbcd/utils/util.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/utils/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"adae040054a625aa","mcp_get_code":{"code_sha256":"adae040054a625aa"}},{"arxiv_id":"2104.06031","paper":"/paper/global-transport-for-fluid-reconstruction","title":"Global Transport for Fluid Reconstruction with Learned Self-Supervision","date":"2021-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tum-pbs/Global-Flow-Transport","path":"phitest/render/optimization.py","file_url":"https://github.com/tum-pbs/Global-Flow-Transport/blob/HEAD/phitest/render/optimization.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"62e39ce4ebceebc9","mcp_get_code":{"code_sha256":"62e39ce4ebceebc9"}},{"arxiv_id":"2103.01955","paper":"/paper/the-surprising-effectiveness-of-mappo-in","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","date":"2021-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"emerge-lab/nocturne_lab","path":"experiments/hr_rl/run_hr_ppo_cli.py","file_url":"https://github.com/emerge-lab/nocturne_lab/blob/HEAD/experiments/hr_rl/run_hr_ppo_cli.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4cee71b4d9b5a737","mcp_get_code":{"code_sha256":"4cee71b4d9b5a737"}},{"arxiv_id":"2007.15255","paper":"/paper/instance-selection-for-gans","title":"Instance Selection for GANs","date":"2020-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"snap-research/3dgp","path":"src/training/loss.py","file_url":"https://github.com/snap-research/3dgp/blob/HEAD/src/training/loss.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"97c1685bb8978f57","mcp_get_code":{"code_sha256":"97c1685bb8978f57"}},{"arxiv_id":"2006.11239","paper":"/paper/denoising-diffusion-probabilistic-models","title":"Denoising Diffusion Probabilistic Models","date":"2020-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tiwarylab/DDPM_REMD","path":"denoising_diffusion_pytorch/denoising_diffusion_pytorch.py","file_url":"https://github.com/tiwarylab/DDPM_REMD/blob/HEAD/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cb41bf2d4dec5aee","mcp_get_code":{"code_sha256":"cb41bf2d4dec5aee"}},{"arxiv_id":"1909.01492","paper":"/paper/achieving-verified-robustness-to-symbol","title":"Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation","date":"2019-09-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepmind/interval-bound-propagation","path":"interval_bound_propagation/src/utils.py","file_url":"https://github.com/deepmind/interval-bound-propagation/blob/HEAD/interval_bound_propagation/src/utils.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":"a60e232adbec82fd","mcp_get_code":{"code_sha256":"a60e232adbec82fd"}},{"arxiv_id":"1710.02298","paper":"/paper/rainbow-combining-improvements-in-deep","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","date":"2017-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"4c60d8998b722013","mcp_get_code":{"code_sha256":"4c60d8998b722013"}}]}