{"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/abstractagent","entry":"AbstractAgent","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":2,"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":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"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":"2505.20642","paper":null,"title":"arXiv:2505.20642","date":null,"month_inferred_from_arxiv_id":"2025-05","title_source":null,"repo":"USTChandsomeboy/CoderAgent","path":"modules/learner_simulation/learner_simulation.py","file_url":"https://github.com/USTChandsomeboy/CoderAgent/blob/HEAD/modules/learner_simulation/learner_simulation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"65d12610cc8c64d4","mcp_get_code":{"code_sha256":"65d12610cc8c64d4"}},{"arxiv_id":"2309.15178","paper":"/paper/conservative-world-models","title":"Zero-Shot Reinforcement Learning from Low Quality Data","date":"2023-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"enjeeneer/conservative-world-models","path":"agents/cfb/agent.py","file_url":"https://github.com/enjeeneer/conservative-world-models/blob/HEAD/agents/cfb/agent.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c45e7cf6e639135","mcp_get_code":{"code_sha256":"5c45e7cf6e639135"}},{"arxiv_id":"2212.00124","paper":"/paper/one-risk-to-rule-them-all-a-risk-sensitive-1","title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning","date":"2022-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nuria95/O-RAAC","path":"oraaclib/agent/ORAAC.py","file_url":"https://github.com/nuria95/O-RAAC/blob/HEAD/oraaclib/agent/ORAAC.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c5bf09ce02ff5964","mcp_get_code":{"code_sha256":"c5bf09ce02ff5964"}},{"arxiv_id":"1801.01290","paper":"/paper/soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"h-aboutalebi/SparceReward","path":"engine/algorithms/SAC/sac.py","file_url":"https://github.com/h-aboutalebi/SparceReward/blob/HEAD/engine/algorithms/SAC/sac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"424bf06f8d8eb998","mcp_get_code":{"code_sha256":"424bf06f8d8eb998"}},{"arxiv_id":"1312.5602","paper":"/paper/playing-atari-with-deep-reinforcement","title":"Playing Atari with Deep Reinforcement Learning","date":"2013-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RLeike/connect-four","path":"agent.py","file_url":"https://github.com/RLeike/connect-four/blob/HEAD/agent.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"26d04828131d058e","mcp_get_code":{"code_sha256":"26d04828131d058e"}}]}