{"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-render-func","entry":"get_render_func","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":0,"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":"2210.03104","paper":"/paper/distributionally-adaptive-meta-reinforcement","title":"Distributionally Adaptive Meta Reinforcement Learning","date":"2022-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ikostrikov/pytorch-a2c-ppo-acktr-gail","path":"a2c_ppo_acktr/utils.py","file_url":"https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail/blob/HEAD/a2c_ppo_acktr/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"108dc9c41448855e","mcp_get_code":{"code_sha256":"108dc9c41448855e"}},{"arxiv_id":"2206.09314","paper":"/paper/robust-imitation-learning-against-variations","title":"Robust Imitation Learning against Variations in Environment Dynamics","date":"2022-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JongseongChae/RIME","path":"algorithm/utils.py","file_url":"https://github.com/JongseongChae/RIME/blob/HEAD/algorithm/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"108dc9c41448855e","mcp_get_code":{"code_sha256":"108dc9c41448855e"}},{"arxiv_id":"2104.07495","paper":"/paper/self-supervised-exploration-via-latent","title":"Curiosity-Driven Exploration via Latent Bayesian Surprise","date":"2021-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mazpie/lbs-exploration","path":"exploration/utils.py","file_url":"https://github.com/mazpie/lbs-exploration/blob/HEAD/exploration/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"108dc9c41448855e","mcp_get_code":{"code_sha256":"108dc9c41448855e"}},{"arxiv_id":"2009.01439","paper":"/paper/dexterous-robotic-grasping-with-object","title":"Learning Dexterous Grasping with Object-Centric Visual Affordances","date":"2020-09-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"priyankamandikal/graff","path":"a2c_ppo_acktr/utils.py","file_url":"https://github.com/priyankamandikal/graff/blob/HEAD/a2c_ppo_acktr/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"108dc9c41448855e","mcp_get_code":{"code_sha256":"108dc9c41448855e"}},{"arxiv_id":"2006.09447","paper":"/paper/opponent-modelling-with-local-information","title":"Agent Modelling under Partial Observability for Deep Reinforcement Learning","date":"2020-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uoe-agents/LIAM","path":"double_speaker_listener/utils.py","file_url":"https://github.com/uoe-agents/LIAM/blob/HEAD/double_speaker_listener/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"108dc9c41448855e","mcp_get_code":{"code_sha256":"108dc9c41448855e"}},{"arxiv_id":"2003.04108","paper":"/paper/stable-policy-optimization-via-off-policy","title":"Stable Policy Optimization via Off-Policy Divergence Regularization","date":"2020-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/ppo-dice","path":"agents/utils.py","file_url":"https://github.com/facebookresearch/ppo-dice/blob/HEAD/agents/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"108dc9c41448855e","mcp_get_code":{"code_sha256":"108dc9c41448855e"}},{"arxiv_id":"1905.04640","paper":"/paper/mega-reward-achieving-human-level-play","title":"Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards","date":"2019-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YuhangSong/Mega-Reward","path":"a2c_ppo_acktr/utils.py","file_url":"https://github.com/YuhangSong/Mega-Reward/blob/HEAD/a2c_ppo_acktr/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"108dc9c41448855e","mcp_get_code":{"code_sha256":"108dc9c41448855e"}}]}