{"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/run-episode","entry":"run_episode","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":10,"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":11,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":9},"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":"2606.23603","paper":"/paper/arxiv-2606-23603","title":"MORL-A2C: Multi-Objective Reinforcement Learning Reranker for Optimizing Healthiness in MOPI-HFRS","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"JoshZ411/MOPI-HFRS-SLC","path":"code/morl/training.py","file_url":"https://github.com/JoshZ411/MOPI-HFRS-SLC/blob/HEAD/code/morl/training.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":"5f992cad961a11bb","mcp_get_code":{"code_sha256":"5f992cad961a11bb"}},{"arxiv_id":"2605.18454","paper":"/paper/arxiv-2605-18454","title":"Scheduling That Speaks: An Interpretable Programmatic Reinforcement Learning Framework","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"HcPlu/ProRL","path":"optimisation/pdr/evaluate.py","file_url":"https://github.com/HcPlu/ProRL/blob/HEAD/optimisation/pdr/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"948517dad8d0fdab","mcp_get_code":{"code_sha256":"948517dad8d0fdab"}},{"arxiv_id":"2309.07388","paper":"/paper/on-autonomous-agents-in-a-cyber-defence","title":"On Autonomous Agents in a Cyber Defence Environment","date":null,"month_inferred_from_arxiv_id":"2023-09","title_source":"archive","repo":"ilyaorson/cyberdreamcatcher","path":"cyberdreamcatcher/sampler.py","file_url":"https://github.com/ilyaorson/cyberdreamcatcher/blob/HEAD/cyberdreamcatcher/sampler.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0b1a16f5749dcc3a","mcp_get_code":{"code_sha256":"0b1a16f5749dcc3a"}},{"arxiv_id":"2011.07831","paper":"/paper/learning-associative-inference-using-fast-1","title":"Learning Associative Inference Using Fast Weight Memory","date":"2020-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ischlag/Fast-Weight-Memory-public","path":"metaRL/train_agent.py","file_url":"https://github.com/ischlag/Fast-Weight-Memory-public/blob/HEAD/metaRL/train_agent.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"83dc00c2fe9d0ac2","mcp_get_code":{"code_sha256":"83dc00c2fe9d0ac2"}},{"arxiv_id":"2006.13760","paper":"/paper/the-nethack-learning-environment","title":"The NetHack Learning Environment","date":"2020-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Pieter-Cawood/Reinforcement-Learning","path":"NLE_Method_Comparison/A2C_1/evaluation.py","file_url":"https://github.com/Pieter-Cawood/Reinforcement-Learning/blob/HEAD/NLE_Method_Comparison/A2C_1/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"38d19bc77768e47c","mcp_get_code":{"code_sha256":"38d19bc77768e47c"}},{"arxiv_id":"2006.07815","paper":"/paper/optimistic-distributionally-robust-policy","title":"Optimistic Distributionally Robust Policy Optimization","date":"2020-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kadysongbb/dr-trpo","path":"tabular/train_helper.py","file_url":"https://github.com/kadysongbb/dr-trpo/blob/HEAD/tabular/train_helper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"376d051ff6f4515b","mcp_get_code":{"code_sha256":"376d051ff6f4515b"}},{"arxiv_id":"1904.00370","paper":"/paper/variational-adversarial-active-learning","title":"Variational Adversarial Active Learning","date":"2019-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"johntiger1/vaal_querying","path":"rl/sample_cartpole.py","file_url":"https://github.com/johntiger1/vaal_querying/blob/HEAD/rl/sample_cartpole.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"baf11f4c9088b555","mcp_get_code":{"code_sha256":"baf11f4c9088b555"}},{"arxiv_id":"1902.01378","paper":"/paper/obstacle-tower-a-generalization-challenge-in","title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","date":"2019-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Unity-Technologies/obstacle-tower-env","path":"examples/evaluation.py","file_url":"https://github.com/Unity-Technologies/obstacle-tower-env/blob/HEAD/examples/evaluation.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"448599b47d160e4f","mcp_get_code":{"code_sha256":"448599b47d160e4f"}},{"arxiv_id":"1805.01956","paper":"/paper/motion-planning-among-dynamic-decision-making","title":"Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning","date":"2018-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mit-acl/gym-collision-avoidance","path":"gym_collision_avoidance/experiments/src/env_utils.py","file_url":"https://github.com/mit-acl/gym-collision-avoidance/blob/HEAD/gym_collision_avoidance/experiments/src/env_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5494e1762df206ef","mcp_get_code":{"code_sha256":"5494e1762df206ef"}},{"arxiv_id":"1710.11198","paper":"/paper/action-depedent-control-variates-for-policy","title":"Action-depedent Control Variates for Policy Optimization via Stein's Identity","date":"2017-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DartML/PPO-Stein-Control-Variate","path":"evaluation/main_algo.py","file_url":"https://github.com/DartML/PPO-Stein-Control-Variate/blob/HEAD/evaluation/main_algo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fe515a034e675f33","mcp_get_code":{"code_sha256":"fe515a034e675f33"}},{"arxiv_id":"1710.11198","paper":"/paper/action-depedent-control-variates-for-policy","title":"Action-depedent Control Variates for Policy Optimization via Stein's Identity","date":"2017-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DartML/PPO-Stein-Control-Variate","path":"optimization/main_algo.py","file_url":"https://github.com/DartML/PPO-Stein-Control-Variate/blob/HEAD/optimization/main_algo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d65e0044847c6ca7","mcp_get_code":{"code_sha256":"d65e0044847c6ca7"}}]}