{"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/get-actor-critic-arch","entry":"get_actor_critic_arch","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":0,"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":2,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"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":"2603.01771","paper":"/paper/arxiv-2603-01771","title":"Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"DLR-RM/stable-baselines3","path":"stable_baselines3/common/torch_layers.py","file_url":"https://github.com/DLR-RM/stable-baselines3/blob/HEAD/stable_baselines3/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb7d59a536215255","mcp_get_code":{"code_sha256":"eb7d59a536215255"}},{"arxiv_id":"2510.20235","paper":"/paper/arxiv-2510-20235","title":"Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"whbyeon/ERAM-ARAM","path":"stable_baselines3/common/torch_layers.py","file_url":"https://github.com/whbyeon/ERAM-ARAM/blob/HEAD/stable_baselines3/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f2ded9c22d608f44","mcp_get_code":{"code_sha256":"f2ded9c22d608f44"}},{"arxiv_id":"2406.07826","paper":"/paper/the-max-min-formulation-of-multi-objective","title":"The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"giseung-park/maxmin-morl","path":"supplementary_ICML24/stable_baselines3/common/torch_layers.py","file_url":"https://github.com/giseung-park/maxmin-morl/blob/HEAD/supplementary_ICML24/stable_baselines3/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f2ded9c22d608f44","mcp_get_code":{"code_sha256":"f2ded9c22d608f44"}},{"arxiv_id":"2205.05138","paper":"/paper/efficient-risk-averse-reinforcement-learning","title":"Efficient Risk-Averse Reinforcement Learning","date":"2022-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fictivename/cesor_ppo","path":"stable_baselines3/common/torch_layers.py","file_url":"https://github.com/fictivename/cesor_ppo/blob/HEAD/stable_baselines3/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2ded9c22d608f44","mcp_get_code":{"code_sha256":"f2ded9c22d608f44"}},{"arxiv_id":"2111.03941","paper":"/paper/time-discretization-invariant-safe-action","title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","date":"2021-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"artberryx/SAR","path":"sb3/stable_baselines3/common/torch_layers.py","file_url":"https://github.com/artberryx/SAR/blob/HEAD/sb3/stable_baselines3/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2ded9c22d608f44","mcp_get_code":{"code_sha256":"f2ded9c22d608f44"}},{"arxiv_id":"2010.14484","paper":"/paper/one-solution-is-not-all-you-need-few-shot","title":"One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL","date":"2020-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"egiob/diversityisallyouneed-sb3","path":"stable_baselines3/common/torch_layers.py","file_url":"https://github.com/egiob/diversityisallyouneed-sb3/blob/HEAD/stable_baselines3/common/torch_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2ded9c22d608f44","mcp_get_code":{"code_sha256":"f2ded9c22d608f44"}}]}