{"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/discount","entry":"discount","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":11,"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":9,"n_samples_ran":2,"n_samples_fingerprinted":2,"n_places":11,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":2,"ran":0,"unverified":7},"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":"2210.17375","paper":"/paper/erl-re-2-efficient-evolutionary-reinforcement","title":"ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation","date":"2022-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yeshenpy/ERL-Re2","path":"core/agent.py","file_url":"https://github.com/yeshenpy/ERL-Re2/blob/HEAD/core/agent.py","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"adb1e03f78b84980","mcp_get_code":{"code_sha256":"adb1e03f78b84980"}},{"arxiv_id":"2010.07916","paper":"/paper/multi-agent-trust-region-policy-optimization","title":"Multi-Agent Trust Region Policy Optimization","date":"2020-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hepengli/matrpo","path":"matrpo/common/math_util.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/math_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"973bd4eccef85757","mcp_get_code":{"code_sha256":"973bd4eccef85757"}},{"arxiv_id":"1907.02874","paper":"/paper/attentive-multi-task-deep-reinforcement","title":"Attentive Multi-Task Deep Reinforcement Learning","date":"2019-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"braemt/attentive-multi-task-deep-reinforcement-learning","path":"a3c.py","file_url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning/blob/HEAD/a3c.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"0ca7ce32a4f2492c","mcp_get_code":{"code_sha256":"0ca7ce32a4f2492c"}},{"arxiv_id":"1906.05226","paper":"/paper/continual-and-multi-task-architecture-search","title":"Continual and Multi-Task Architecture Search","date":"2019-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ramakanth-pasunuru/CAS-MAS","path":"trainer.py","file_url":"https://github.com/ramakanth-pasunuru/CAS-MAS/blob/HEAD/trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc015b361f3178c7","mcp_get_code":{"code_sha256":"cc015b361f3178c7"}},{"arxiv_id":"1904.10729","paper":"/paper/neural-logic-reinforcement-learning","title":"Neural Logic Reinforcement Learning","date":"2019-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhengyaoJiang/NLRL","path":"core/rl.py","file_url":"https://github.com/ZhengyaoJiang/NLRL/blob/HEAD/core/rl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7767b1b80f46ddeb","mcp_get_code":{"code_sha256":"7767b1b80f46ddeb"}},{"arxiv_id":"1904.09981","paper":"/paper/graphnas-graph-neural-architecture-search","title":"GraphNAS: Graph Neural Architecture Search with Reinforcement Learning","date":"2019-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GraphNAS/GraphNAS-simple","path":"graphnas/trainer.py","file_url":"https://github.com/GraphNAS/GraphNAS-simple/blob/HEAD/graphnas/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":"35a7fa611d2a624f","mcp_get_code":{"code_sha256":"35a7fa611d2a624f"}},{"arxiv_id":"1810.12894","paper":"/paper/exploration-by-random-network-distillation","title":"Exploration by Random Network Distillation","date":"2018-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/strategically_efficient_rl","path":"algorithms/agents/intrinsic.py","file_url":"https://github.com/microsoft/strategically_efficient_rl/blob/HEAD/algorithms/agents/intrinsic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0ca7ce32a4f2492c","mcp_get_code":{"code_sha256":"0ca7ce32a4f2492c"}},{"arxiv_id":"1706.01905","paper":"/paper/parameter-space-noise-for-exploration","title":"Parameter Space Noise for Exploration","date":"2017-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aspk/Tensorflow_Deep_RL","path":"param_noise_mlp.py","file_url":"https://github.com/aspk/Tensorflow_Deep_RL/blob/HEAD/param_noise_mlp.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c80e4e6524f7b68e","mcp_get_code":{"code_sha256":"c80e4e6524f7b68e"}},{"arxiv_id":"1703.01988","paper":"/paper/neural-episodic-control","title":"Neural Episodic Control","date":"2017-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mjacar/pytorch-nec","path":"utils/math_utils.py","file_url":"https://github.com/mjacar/pytorch-nec/blob/HEAD/utils/math_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59e3e825c388becc","mcp_get_code":{"code_sha256":"59e3e825c388becc"}},{"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":"awjuliani/Meta-RL","path":"helper.py","file_url":"https://github.com/awjuliani/Meta-RL/blob/HEAD/helper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fb210a4cf2658a85","mcp_get_code":{"code_sha256":"fb210a4cf2658a85"}},{"arxiv_id":"1602.01783","paper":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/universe-starter-agent","path":"a3c.py","file_url":"https://github.com/openai/universe-starter-agent/blob/HEAD/a3c.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0ca7ce32a4f2492c","mcp_get_code":{"code_sha256":"0ca7ce32a4f2492c"}}]}