{"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/test-agent","entry":"test_agent","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":5,"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":4,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":2,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":2},"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":"2605.19503","paper":"/paper/arxiv-2605-19503","title":"ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"CarloRomeo427/ARC_RL","path":"src/algos/core.py","file_url":"https://github.com/CarloRomeo427/ARC_RL/blob/HEAD/src/algos/core.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"977de6bae6c0ba44","mcp_get_code":{"code_sha256":"977de6bae6c0ba44"}},{"arxiv_id":"2605.05863","paper":"/paper/arxiv-2605-05863","title":"SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"CarloRomeo427/SOPE","path":"src/algos/agent_sope.py","file_url":"https://github.com/CarloRomeo427/SOPE/blob/HEAD/src/algos/agent_sope.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"977de6bae6c0ba44","mcp_get_code":{"code_sha256":"977de6bae6c0ba44"}},{"arxiv_id":"2407.03969","paper":"/paper/craftium-an-extensible-framework-for-creating","title":"Craftium: An Extensible Framework for Creating Reinforcement Learning Environments","date":"2024-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mikelma/craftium","path":"marl_self_play.py","file_url":"https://github.com/mikelma/craftium/blob/HEAD/marl_self_play.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"87eb76037fde12bd","mcp_get_code":{"code_sha256":"87eb76037fde12bd"}},{"arxiv_id":"2110.02034","paper":"/paper/dropout-q-functions-for-doubly-efficient","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","date":"2021-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"takuyahiraoka/dropout-q-functions-for-doubly-efficient-reinforcement-learning","path":"OriginalREDQCodebase/redq/algos/core.py","file_url":"https://github.com/takuyahiraoka/dropout-q-functions-for-doubly-efficient-reinforcement-learning/blob/HEAD/OriginalREDQCodebase/redq/algos/core.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88623398df64361e","mcp_get_code":{"code_sha256":"88623398df64361e"}},{"arxiv_id":"1810.09202","paper":"/paper/graph-convolutional-reinforcement-learning","title":"Graph Convolutional Reinforcement Learning","date":"2018-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiechuanjiang/pytorch_dgn","path":"Starcraft/DGN/utilis.py","file_url":"https://github.com/jiechuanjiang/pytorch_dgn/blob/HEAD/Starcraft/DGN/utilis.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"94c245f3452a240e","mcp_get_code":{"code_sha256":"94c245f3452a240e"}}]}