{"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/combined-shape","entry":"combined_shape","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":16,"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":3,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":16,"n_places_pointer_only":5,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":1},"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":"2605.11975","paper":"/paper/arxiv-2605-11975","title":"Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"milanganai/milanganai.github.io","path":"NeurIPS2023/code/core_respo.py","file_url":"https://github.com/milanganai/milanganai.github.io/blob/HEAD/NeurIPS2023/code/core_respo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}},{"arxiv_id":"2605.09638","paper":"/paper/arxiv-2605-09638","title":"Plan2Cleanse: Test-Time Backdoor Defense via Monte-Carlo Planning in Deep Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"rl-bandits-lab/RL-Backdoor","path":"backdoor_attack/multiagent_competition/fast_failing/train/ppo_core.py","file_url":"https://github.com/rl-bandits-lab/RL-Backdoor/blob/HEAD/backdoor_attack/multiagent_competition/fast_failing/train/ppo_core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}},{"arxiv_id":"2501.17827","paper":"/paper/langevin-soft-actor-critic-efficient","title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning","date":"2025-01-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hmishfaq/lsac","path":"lsac.py","file_url":"https://github.com/hmishfaq/lsac/blob/HEAD/lsac.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6d24f19c56e16f4a","mcp_get_code":{"code_sha256":"6d24f19c56e16f4a"}},{"arxiv_id":"2302.14833","paper":"/paper/learning-to-control-autonomous-fleets-from","title":"Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning","date":"2023-02-28","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":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}},{"arxiv_id":"2302.00808","paper":"/paper/average-constrained-policy-optimization","title":"ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints","date":"2023-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/safety-starter-agents","path":"safe_rl/pg/utils.py","file_url":"https://github.com/openai/safety-starter-agents/blob/HEAD/safe_rl/pg/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}},{"arxiv_id":"2210.07573","paper":"/paper/model-based-safe-deep-reinforcement-learning","title":"Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm","date":"2022-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akjayant/mbppol","path":"src/core.py","file_url":"https://github.com/akjayant/mbppol/blob/HEAD/src/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}},{"arxiv_id":"2205.14842","paper":"/paper/efficient-reward-poisoning-attacks-on-online","title":"Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning","date":"2022-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yinglunxu/reward_poisoning_attack_drl","path":"src/all_class.py","file_url":"https://github.com/yinglunxu/reward_poisoning_attack_drl/blob/HEAD/src/all_class.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}},{"arxiv_id":"2110.01219","paper":"/paper/hit-and-lead-discovery-with-explorative-rl","title":"Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation","date":"2021-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AITRICS/FREED","path":"core_motif.py","file_url":"https://github.com/AITRICS/FREED/blob/HEAD/core_motif.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}},{"arxiv_id":"2109.12286","paper":"/paper/stackelberg-actor-critic-game-theoretic","title":"Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms","date":"2021-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leozhengzly/stackelberg-actor-critic-algos","path":"spinup/algos/pytorch/ddpg/core.py","file_url":"https://github.com/leozhengzly/stackelberg-actor-critic-algos/blob/HEAD/spinup/algos/pytorch/ddpg/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}},{"arxiv_id":"2108.03952","paper":"/paper/safe-deep-reinforcement-learning-for-multi","title":"Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces","date":"2021-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zisikons/deep-rl","path":"core/DDPG.py","file_url":"https://github.com/zisikons/deep-rl/blob/HEAD/core/DDPG.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c8c447e6d29472c4","mcp_get_code":{"code_sha256":"c8c447e6d29472c4"}},{"arxiv_id":"2106.09110","paper":"/paper/safe-reinforcement-learning-using-advantage","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","date":"2021-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nolanwagener/safe_rl","path":"safe_rl/algos/cppo/core.py","file_url":"https://github.com/nolanwagener/safe_rl/blob/HEAD/safe_rl/algos/cppo/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}},{"arxiv_id":"2010.09635","paper":"/paper/deep-reinforcement-learning-with-population","title":"Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Control","date":"2020-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"combra-lab/pop-spiking-deep-rl","path":"popsan_drl/popsan_sac/core_cuda.py","file_url":"https://github.com/combra-lab/pop-spiking-deep-rl/blob/HEAD/popsan_drl/popsan_sac/core_cuda.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}},{"arxiv_id":"2006.07442","paper":"/paper/self-imitation-learning-via-generalized-lower","title":"Self-Imitation Learning via Generalized Lower Bound Q-learning","date":"2020-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/spinningup","path":"spinup/algos/pytorch/ddpg/core.py","file_url":"https://github.com/openai/spinningup/blob/HEAD/spinup/algos/pytorch/ddpg/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}},{"arxiv_id":"1912.13465","paper":"/paper/reward-conditioned-policies","title":"Reward-Conditioned Policies","date":"2019-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TrentBrick/RewardConditionedUDRL","path":"utils/buffer.py","file_url":"https://github.com/TrentBrick/RewardConditionedUDRL/blob/HEAD/utils/buffer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}},{"arxiv_id":"1906.06818","paper":"/paper/stacked-capsule-autoencoders","title":"Stacked Capsule Autoencoders","date":"2019-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KohavTal/SCAE_Project","path":"torch_scae/general_utils.py","file_url":"https://github.com/KohavTal/SCAE_Project/blob/HEAD/torch_scae/general_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}},{"arxiv_id":"aaai_35251","paper":null,"title":"arXiv:aaai_35251","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Teddy298/continualworld-ppo","path":"continualworld/ppo/core.py","file_url":"https://github.com/Teddy298/continualworld-ppo/blob/HEAD/continualworld/ppo/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57542f87e248db45","mcp_get_code":{"code_sha256":"57542f87e248db45"}}]}