{"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/sf01","entry":"sf01","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":9,"n_papers_ran":9,"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":1,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":0},"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":"2101.08152","paper":"/paper/rank-the-episodes-a-simple-approach-for-1","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","date":"2021-01-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"daochenzha/rapid","path":"rapid/agent.py","file_url":"https://github.com/daochenzha/rapid/blob/HEAD/rapid/agent.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"baf2a28d376d7803","mcp_get_code":{"code_sha256":"baf2a28d376d7803"}},{"arxiv_id":"1912.01588","paper":"/paper/leveraging-procedural-generation-to-benchmark","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","date":"2019-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ana-tudor/classyconditioning","path":"fruitbot_ppo/epopt_runner.py","file_url":"https://github.com/ana-tudor/classyconditioning/blob/HEAD/fruitbot_ppo/epopt_runner.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"baf2a28d376d7803","mcp_get_code":{"code_sha256":"baf2a28d376d7803"}},{"arxiv_id":"1910.05396","paper":"/paper/a-simple-randomization-technique-for-1","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","date":"2019-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pokaxpoka/netrand","path":"sources/ppo2.py","file_url":"https://github.com/pokaxpoka/netrand/blob/HEAD/sources/ppo2.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"baf2a28d376d7803","mcp_get_code":{"code_sha256":"baf2a28d376d7803"}},{"arxiv_id":"1905.04819","paper":"/paper/task-agnostic-dynamics-priors-for-deep","title":"Task-Agnostic Dynamics Priors for Deep Reinforcement Learning","date":"2019-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"baf2a28d376d7803","mcp_get_code":{"code_sha256":"baf2a28d376d7803"}},{"arxiv_id":"1905.02363","paper":"/paper/dimension-wise-importance-sampling-weight","title":"Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning","date":"2019-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seungyulhan/disc","path":"baselines/DISC/DISC.py","file_url":"https://github.com/seungyulhan/disc/blob/HEAD/baselines/DISC/DISC.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"baf2a28d376d7803","mcp_get_code":{"code_sha256":"baf2a28d376d7803"}},{"arxiv_id":"1902.00255","paper":"/paper/policy-consolidation-for-continual","title":"Policy Consolidation for Continual Reinforcement Learning","date":"2019-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"baf2a28d376d7803","mcp_get_code":{"code_sha256":"baf2a28d376d7803"}},{"arxiv_id":"1812.02341","paper":"/paper/quantifying-generalization-in-reinforcement","title":"Quantifying Generalization in Reinforcement Learning","date":"2018-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/coinrun","path":"coinrun/ppo2.py","file_url":"https://github.com/openai/coinrun/blob/HEAD/coinrun/ppo2.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"baf2a28d376d7803","mcp_get_code":{"code_sha256":"baf2a28d376d7803"}},{"arxiv_id":"1806.07857","paper":"/paper/rudder-return-decomposition-for-delayed","title":"RUDDER: Return Decomposition for Delayed Rewards","date":"2018-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-jku/baselines-rudder","path":"baselines/ppo2_rudder/ppo2_rudder.py","file_url":"https://github.com/ml-jku/baselines-rudder/blob/HEAD/baselines/ppo2_rudder/ppo2_rudder.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"baf2a28d376d7803","mcp_get_code":{"code_sha256":"baf2a28d376d7803"}},{"arxiv_id":"1707.06347","paper":"/paper/proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"baf2a28d376d7803","mcp_get_code":{"code_sha256":"baf2a28d376d7803"}}]}