{"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/load-policy","entry":"load_policy","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":9,"n_papers_ran":1,"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":10,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"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":"2608.25419","paper":"/paper/arxiv-2608-25419","title":"BVR Sim: An Open and High-Throughput Environment for Heterogeneous Air-Combat Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"lizi-Margin/bvr_sim","path":"bvr_sim_rl/evaluate.py","file_url":"https://github.com/lizi-Margin/bvr_sim/blob/HEAD/bvr_sim_rl/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"7dad9e7a7ddc77b3","mcp_get_code":{"code_sha256":"7dad9e7a7ddc77b3"}},{"arxiv_id":"2605.21311","paper":"/paper/arxiv-2605-21311","title":"DeCoR: Design and Control Co-Optimization for Urban Streets Using Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"poudel-bibek/DeCoR","path":"utils.py","file_url":"https://github.com/poudel-bibek/DeCoR/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a8fe218a1db0a77a","mcp_get_code":{"code_sha256":"a8fe218a1db0a77a"}},{"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/zoo_agent_pytorch.py","file_url":"https://github.com/rl-bandits-lab/RL-Backdoor/blob/HEAD/backdoor_attack/multiagent_competition/zoo_agent_pytorch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"0b5387c253c3fea7","mcp_get_code":{"code_sha256":"0b5387c253c3fea7"}},{"arxiv_id":"2409.05344","paper":"/paper/gopt-generalizable-online-3d-bin-packing-via","title":"GOPT: Generalizable Online 3D Bin Packing via Transformer-based Deep Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2024-09","title_source":"archive","repo":"xiong5heng/gopt","path":"tools.py","file_url":"https://github.com/xiong5heng/gopt/blob/HEAD/tools.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dc0bd7d5c02cdbf3","mcp_get_code":{"code_sha256":"dc0bd7d5c02cdbf3"}},{"arxiv_id":"2210.04839","paper":"/paper/benchmarking-reinforcement-learning-1","title":"Benchmarking Reinforcement Learning Techniques for Autonomous Navigation","date":"2022-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Daffan/ros_jackal","path":"actor.py","file_url":"https://github.com/Daffan/ros_jackal/blob/HEAD/actor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8883a16afb4b4d46","mcp_get_code":{"code_sha256":"8883a16afb4b4d46"}},{"arxiv_id":"2210.04839","paper":"/paper/benchmarking-reinforcement-learning-1","title":"Benchmarking Reinforcement Learning Techniques for Autonomous Navigation","date":"2022-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Daffan/ros_jackal","path":"rl_algos/tester.py","file_url":"https://github.com/Daffan/ros_jackal/blob/HEAD/rl_algos/tester.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c51ea62545640750","mcp_get_code":{"code_sha256":"c51ea62545640750"}},{"arxiv_id":"2004.07219","paper":"/paper/datasets-for-data-driven-reinforcement","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","date":"2020-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"farama-foundation/d4rl","path":"scripts/generation/generate_ant_maze_datasets.py","file_url":"https://github.com/farama-foundation/d4rl/blob/HEAD/scripts/generation/generate_ant_maze_datasets.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":"3cf6d03023b905d7","mcp_get_code":{"code_sha256":"3cf6d03023b905d7"}},{"arxiv_id":"1910.04700","paper":"/paper/assistive-gym-a-physics-simulation-framework","title":"Assistive Gym: A Physics Simulation Framework for Assistive Robotics","date":"2019-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"titardrew/assistive-gym","path":"assistive_gym/learn.py","file_url":"https://github.com/titardrew/assistive-gym/blob/HEAD/assistive_gym/learn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"46a922fa94ebb95a","mcp_get_code":{"code_sha256":"46a922fa94ebb95a"}},{"arxiv_id":"1812.06298","paper":"/paper/residual-policy-learning","title":"Residual Policy Learning","date":"2018-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"k-r-allen/residual-policy-learning","path":"tensorflow/experiment/train_residual_base.py","file_url":"https://github.com/k-r-allen/residual-policy-learning/blob/HEAD/tensorflow/experiment/train_residual_base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d7f89832be19bfa8","mcp_get_code":{"code_sha256":"d7f89832be19bfa8"}},{"arxiv_id":"1810.02274","paper":"/paper/episodic-curiosity-through-reachability","title":"Episodic Curiosity through Reachability","date":"2018-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/episodic-curiosity","path":"episodic_curiosity/curiosity_evaluation.py","file_url":"https://github.com/google-research/episodic-curiosity/blob/HEAD/episodic_curiosity/curiosity_evaluation.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":"c2bbba3d603b4193","mcp_get_code":{"code_sha256":"c2bbba3d603b4193"}}]}