{"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/actorcriticnetwork","entry":"ActorCriticNetwork","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":5,"n_samples_ran":3,"n_samples_fingerprinted":1,"n_places":5,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"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":"2603.24738","paper":"/paper/arxiv-2603-24738","title":"Decentralized Task Scheduling in Distributed Systems: A Deep Reinforcement Learning Approach","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"danielbenniah/marl-distributed-scheduling","path":"marl_scheduler.py","file_url":"https://github.com/danielbenniah/marl-distributed-scheduling/blob/HEAD/marl_scheduler.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3e5b23e26d907456","mcp_get_code":{"code_sha256":"3e5b23e26d907456"}},{"arxiv_id":"2602.06025","paper":"/paper/arxiv-2602-06025","title":"Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"ViktorAxelsen/BudgetMem","path":"src/trainer/ppo_trainer.py","file_url":"https://github.com/ViktorAxelsen/BudgetMem/blob/HEAD/src/trainer/ppo_trainer.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":"f7c912ccfce8d065","mcp_get_code":{"code_sha256":"f7c912ccfce8d065"}},{"arxiv_id":"2406.09899","paper":"/paper/learning-solution-aware-transformers-for","title":"Learning Solution-Aware Transformers for Efficiently Solving Quadratic Assignment Problem","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pkutan/sawt","path":"ActorCriticNetwork_qap_mixEncoder.py","file_url":"https://github.com/pkutan/sawt/blob/HEAD/ActorCriticNetwork_qap_mixEncoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dcb619a621a712da","mcp_get_code":{"code_sha256":"dcb619a621a712da"}},{"arxiv_id":"2210.09598","paper":"/paper/planning-for-sample-efficient-imitation","title":"Planning for Sample Efficient Imitation Learning","date":"2022-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaohengyin/EfficientImitate","path":"algo/obs_ei/model.py","file_url":"https://github.com/zhaohengyin/EfficientImitate/blob/HEAD/algo/obs_ei/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"89159fd394eef8da","mcp_get_code":{"code_sha256":"89159fd394eef8da"}},{"arxiv_id":"1509.02971","paper":"/paper/continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","date":"2015-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arnomoonens/yarll","path":"yarll/agents/tf2/actorcritic/actor_critic.py","file_url":"https://github.com/arnomoonens/yarll/blob/HEAD/yarll/agents/tf2/actorcritic/actor_critic.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"491a0ea3930828b7","mcp_get_code":{"code_sha256":"491a0ea3930828b7"}}]}