{"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/orthogonal-init","entry":"orthogonal_init","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":12,"n_papers_ran":4,"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":4,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":3,"unverified":8},"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":"2605.06156","paper":"/paper/arxiv-2605-06156","title":"Entropy-Regularized Adjoint Matching for Offline Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"ColinQiyangLi/qam","path":"agents/model.py","file_url":"https://github.com/ColinQiyangLi/qam/blob/HEAD/agents/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"97135b7e661acbd2","mcp_get_code":{"code_sha256":"97135b7e661acbd2"}},{"arxiv_id":"2502.15280","paper":"/paper/hyperspherical-normalization-for-scalable","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","date":"2025-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SonyResearch/simba","path":"scale_rl/networks/layers.py","file_url":"https://github.com/SonyResearch/simba/blob/HEAD/scale_rl/networks/layers.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5ac49b3249fc3ab0","mcp_get_code":{"code_sha256":"5ac49b3249fc3ab0"}},{"arxiv_id":"2410.22728","paper":"/paper/offline-behavior-distillation","title":"Offline Behavior Distillation","date":"2024-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leaveslei/obd","path":"data_lib/syndset.py","file_url":"https://github.com/leaveslei/obd/blob/HEAD/data_lib/syndset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1ec0ea84d63a7360","mcp_get_code":{"code_sha256":"1ec0ea84d63a7360"}},{"arxiv_id":"2410.18076","paper":"/paper/leveraging-skills-from-unlabeled-prior-data","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rail-berkeley/supe","path":"supe/agents/model.py","file_url":"https://github.com/rail-berkeley/supe/blob/HEAD/supe/agents/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f86bee8890076da","mcp_get_code":{"code_sha256":"7f86bee8890076da"}},{"arxiv_id":"2405.20555","paper":"/paper/diffusion-actor-critic-formulating","title":"Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Fang-Lin93/DAC","path":"networks/initialization.py","file_url":"https://github.com/Fang-Lin93/DAC/blob/HEAD/networks/initialization.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"87c04751d25ad6e2","mcp_get_code":{"code_sha256":"87c04751d25ad6e2"}},{"arxiv_id":"2405.14114","paper":"/paper/offline-reinforcement-learning-from-datasets","title":"Offline Reinforcement Learning from Datasets with Structured Non-Stationarity","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"johannesack/offlinerlstructurednonstationarity","path":"RLMethods/rl_models.py","file_url":"https://github.com/johannesack/offlinerlstructurednonstationarity/blob/HEAD/RLMethods/rl_models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0e1815d7327a86a7","mcp_get_code":{"code_sha256":"0e1815d7327a86a7"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"20ae3914de637dd8","mcp_get_code":{"code_sha256":"20ae3914de637dd8"}},{"arxiv_id":"2307.08875","paper":"/paper/natural-actor-critic-for-robust-reinforcement","title":"Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation","date":"2023-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tliu1997/rnac","path":"train_rnac.py","file_url":"https://github.com/tliu1997/rnac/blob/HEAD/train_rnac.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aaec1511480533d6","mcp_get_code":{"code_sha256":"aaec1511480533d6"}},{"arxiv_id":"2205.12258","paper":"/paper/history-compression-via-language-models-in","title":"History Compression via Language Models in Reinforcement Learning","date":"2022-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-jku/helm","path":"model.py","file_url":"https://github.com/ml-jku/helm/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"60f8e59fbca2965d","mcp_get_code":{"code_sha256":"60f8e59fbca2965d"}},{"arxiv_id":"2105.14111","paper":"/paper/objective-robustness-in-deep-reinforcement","title":"Goal Misgeneralization in Deep Reinforcement Learning","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UlisseMini/procgen-tools","path":"procgen_tools/models.py","file_url":"https://github.com/UlisseMini/procgen-tools/blob/HEAD/procgen_tools/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"91b1e1870bc40fd3","mcp_get_code":{"code_sha256":"91b1e1870bc40fd3"}},{"arxiv_id":"2006.11751","paper":"/paper/sample-factory-egocentric-3d-control-from","title":"Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning","date":"2020-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alex-petrenko/sample-factory","path":"sample_factory/model/utils.py","file_url":"https://github.com/alex-petrenko/sample-factory/blob/HEAD/sample_factory/model/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ec56f732ad5319e0","mcp_get_code":{"code_sha256":"ec56f732ad5319e0"}},{"arxiv_id":"1703.06907","paper":"/paper/domain-randomization-for-transferring-deep","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","date":"2017-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xinjinghao/sparrow-v1","path":"train_DDQN_vector.py","file_url":"https://github.com/xinjinghao/sparrow-v1/blob/HEAD/train_DDQN_vector.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b39a7fac162179b","mcp_get_code":{"code_sha256":"9b39a7fac162179b"}}]}