{"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/ortho-init","entry":"ortho_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":7,"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":7,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":0,"unverified":4},"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":"2403.10760","paper":"/paper/corn-contact-based-object-representation-for","title":"CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects","date":null,"month_inferred_from_arxiv_id":"2024-03","title_source":"archive","repo":"contact-non-prehensile/corn","path":"pkm/src/pkm/models/rl/nets.py","file_url":"https://github.com/contact-non-prehensile/corn/blob/HEAD/pkm/src/pkm/models/rl/nets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f08bd01d6576b1b1","mcp_get_code":{"code_sha256":"f08bd01d6576b1b1"}},{"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":"sb/stable_baselines/common/tf_layers.py","file_url":"https://github.com/artberryx/SAR/blob/HEAD/sb/stable_baselines/common/tf_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90935b4a6d887717","mcp_get_code":{"code_sha256":"90935b4a6d887717"}},{"arxiv_id":"2105.13345","paper":"/paper/adversarial-intrinsic-motivation-for","title":"Adversarial Intrinsic Motivation for Reinforcement Learning","date":"2021-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iDurugkar/adversarial-intrinsic-motivation","path":"stable_baselines/common/tf_layers.py","file_url":"https://github.com/iDurugkar/adversarial-intrinsic-motivation/blob/HEAD/stable_baselines/common/tf_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90935b4a6d887717","mcp_get_code":{"code_sha256":"90935b4a6d887717"}},{"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/models/fc.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/models/fc.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":"0cb9b8299fe38738","mcp_get_code":{"code_sha256":"0cb9b8299fe38738"}},{"arxiv_id":"2010.07916","paper":"/paper/multi-agent-trust-region-policy-optimization","title":"Multi-Agent Trust Region Policy Optimization","date":"2020-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hepengli/matrpo","path":"matrpo/common/models.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/models.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":"0cb9b8299fe38738","mcp_get_code":{"code_sha256":"0cb9b8299fe38738"}},{"arxiv_id":"2010.07777","paper":"/paper/a-game-theoretic-analysis-of-networked-system","title":"A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning","date":"2020-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"instadeepai/EGTA-NMARL","path":"egta/agents/utils.py","file_url":"https://github.com/instadeepai/EGTA-NMARL/blob/HEAD/egta/agents/utils.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":"6583a667fee3e221","mcp_get_code":{"code_sha256":"6583a667fee3e221"}},{"arxiv_id":"2004.01339","paper":"/paper/multi-agent-reinforcement-learning-for-2","title":"Multi-agent Reinforcement Learning for Networked System Control","date":"2020-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cts198859/deeprl_network","path":"agents/models.py","file_url":"https://github.com/cts198859/deeprl_network/blob/HEAD/agents/models.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6583a667fee3e221","mcp_get_code":{"code_sha256":"6583a667fee3e221"}},{"arxiv_id":"2001.03415","paper":"/paper/multi-agent-interactions-modeling-with-1","title":"Multi-Agent Interactions Modeling with Correlated Policies","date":"2020-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apexrl/CoDAIL","path":"multi-agent-irl/irl/mack/kfac_discriminator_codail.py","file_url":"https://github.com/apexrl/CoDAIL/blob/HEAD/multi-agent-irl/irl/mack/kfac_discriminator_codail.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":"0cb9b8299fe38738","mcp_get_code":{"code_sha256":"0cb9b8299fe38738"}},{"arxiv_id":"1903.04527","paper":"/paper/multi-agent-deep-reinforcement-learning-for-2","title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","date":"2019-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cts198859/deeprl_signal_control","path":"agents/utils.py","file_url":"https://github.com/cts198859/deeprl_signal_control/blob/HEAD/agents/utils.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":"6583a667fee3e221","mcp_get_code":{"code_sha256":"6583a667fee3e221"}},{"arxiv_id":"1801.01290","paper":"/paper/soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yhisaki/average-reward-drl","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/sac.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c5bce3523ed4d69","mcp_get_code":{"code_sha256":"5c5bce3523ed4d69"}},{"arxiv_id":"1710.11417","paper":"/paper/treeqn-and-atreec-differentiable-tree","title":"TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning","date":"2017-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oxwhirl/treeqn","path":"treeqn/utils/pytorch_utils.py","file_url":"https://github.com/oxwhirl/treeqn/blob/HEAD/treeqn/utils/pytorch_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aec7854e1d8f8fc2","mcp_get_code":{"code_sha256":"aec7854e1d8f8fc2"}},{"arxiv_id":"1602.01783","paper":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qihongl/demo-advantage-actor-critic","path":"src/models/_A2C_discrete.py","file_url":"https://github.com/qihongl/demo-advantage-actor-critic/blob/HEAD/src/models/_A2C_discrete.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3f6057b22a1416fa","mcp_get_code":{"code_sha256":"3f6057b22a1416fa"}}]}