{"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/cat-entropy-softmax","entry":"cat_entropy_softmax","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":7,"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":1,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":1},"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":"2302.02299","paper":"/paper/sample-dropout-a-simple-yet-effective","title":"Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization","date":"2023-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linzichuan/sdpo","path":"baselines/a2c/utils.py","file_url":"https://github.com/linzichuan/sdpo/blob/HEAD/baselines/a2c/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"7082b4bbc0d9384f","mcp_get_code":{"code_sha256":"7082b4bbc0d9384f"}},{"arxiv_id":"2006.04061","paper":"/paper/dual-policy-distillation","title":"Dual Policy Distillation","date":"2020-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kiminh/dual-policy-distillation","path":"baselines/a2c/utils.py","file_url":"https://github.com/kiminh/dual-policy-distillation/blob/HEAD/baselines/a2c/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"7082b4bbc0d9384f","mcp_get_code":{"code_sha256":"7082b4bbc0d9384f"}},{"arxiv_id":"1905.06750","paper":"/paper/random-expert-distillation-imitation-learning","title":"Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation","date":"2019-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RuohanW/RED","path":"baselines/a2c/utils.py","file_url":"https://github.com/RuohanW/RED/blob/HEAD/baselines/a2c/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"7082b4bbc0d9384f","mcp_get_code":{"code_sha256":"7082b4bbc0d9384f"}},{"arxiv_id":"1905.04100","paper":"/paper/190504100","title":"Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization","date":"2019-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aralab-unr/ReinforcementLearningWithGA","path":"baselines/a2c/utils.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/baselines/a2c/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"7082b4bbc0d9384f","mcp_get_code":{"code_sha256":"7082b4bbc0d9384f"}},{"arxiv_id":"1804.06459","paper":"/paper/on-learning-intrinsic-rewards-for-policy","title":"On Learning Intrinsic Rewards for Policy Gradient Methods","date":"2018-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Hwhitetooth/lirpg","path":"baselines/a2c/utils.py","file_url":"https://github.com/Hwhitetooth/lirpg/blob/HEAD/baselines/a2c/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"7082b4bbc0d9384f","mcp_get_code":{"code_sha256":"7082b4bbc0d9384f"}},{"arxiv_id":"1711.00123","paper":"/paper/backpropagation-through-the-void-optimizing","title":"Backpropagation through the Void: Optimizing control variates for black-box gradient estimation","date":"2017-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wgrathwohl/BackpropThroughTheVoidRL","path":"baselines/a2c/utils.py","file_url":"https://github.com/wgrathwohl/BackpropThroughTheVoidRL/blob/HEAD/baselines/a2c/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"7082b4bbc0d9384f","mcp_get_code":{"code_sha256":"7082b4bbc0d9384f"}},{"arxiv_id":"1611.05763","paper":"/paper/learning-to-reinforcement-learn","title":"Learning to reinforcement learn","date":"2016-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gomerudo/openai-baselines","path":"baselines/a2c/utils.py","file_url":"https://github.com/gomerudo/openai-baselines/blob/HEAD/baselines/a2c/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"7082b4bbc0d9384f","mcp_get_code":{"code_sha256":"7082b4bbc0d9384f"}}]}