{"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/value-iteration","entry":"value_iteration","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":6,"n_papers_ran":3,"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":6,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":1,"ran":0,"unverified":3},"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":"2406.00120","paper":"/paper/reward-machines-for-deep-rl-in-noisy-and","title":"Reward Machines for Deep RL in Noisy and Uncertain Environments","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andrewli77/reward-machines-noisy-environments","path":"src/reward_machines/reward_machine_utils.py","file_url":"https://github.com/andrewli77/reward-machines-noisy-environments/blob/HEAD/src/reward_machines/reward_machine_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f1e0170748710dcd","mcp_get_code":{"code_sha256":"f1e0170748710dcd"}},{"arxiv_id":"2207.08645","paper":"/paper/active-exploration-for-inverse-reinforcement","title":"Active Exploration for Inverse Reinforcement Learning","date":"2022-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lasgroup/aceirl","path":"src/active_irl/aceirl/algorithm.py","file_url":"https://github.com/lasgroup/aceirl/blob/HEAD/src/active_irl/aceirl/algorithm.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"09b98208eac525f2","mcp_get_code":{"code_sha256":"09b98208eac525f2"}},{"arxiv_id":"2205.12532","paper":"/paper/skill-machines-temporal-logic-composition-in","title":"Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning","date":"2022-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"geraudnt/skill_machines","path":"sm.py","file_url":"https://github.com/geraudnt/skill_machines/blob/HEAD/sm.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":"31d45b6fb19acf41","mcp_get_code":{"code_sha256":"31d45b6fb19acf41"}},{"arxiv_id":"2109.07171","paper":"/paper/balancing-detectability-and-performance-of","title":"Balancing detectability and performance of attacks on the control channel of Markov Decision Processes","date":"2021-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rssalessio/optimal-attack-control-channel-mdp","path":"inventory_management_problem/utils.py","file_url":"https://github.com/rssalessio/optimal-attack-control-channel-mdp/blob/HEAD/inventory_management_problem/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"92644ea24d460ab0","mcp_get_code":{"code_sha256":"92644ea24d460ab0"}},{"arxiv_id":"2106.04696","paper":"/paper/curriculum-design-for-teaching-via","title":"Curriculum Design for Teaching via Demonstrations: Theory and Applications","date":"2021-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adishs/neurips2021_curriculum-teaching-demonstrations_code","path":"code_cardriving/IRL/teacher.py","file_url":"https://github.com/adishs/neurips2021_curriculum-teaching-demonstrations_code/blob/HEAD/code_cardriving/IRL/teacher.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fd4cee10d947a7f2","mcp_get_code":{"code_sha256":"fd4cee10d947a7f2"}},{"arxiv_id":"1802.06070","paper":"/paper/diversity-is-all-you-need-learning-skills","title":"Diversity is All You Need: Learning Skills without a Reward Function","date":"2018-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"navneet-nmk/Hierarchical-Meta-Reinforcement-Learning","path":"maml_rl/utils/reinforcement_learning.py","file_url":"https://github.com/navneet-nmk/Hierarchical-Meta-Reinforcement-Learning/blob/HEAD/maml_rl/utils/reinforcement_learning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9bb3898b9bf31939","mcp_get_code":{"code_sha256":"9bb3898b9bf31939"}}]}