{"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/evaluate-policy","entry":"evaluate_policy","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":12,"n_papers_ran":7,"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":14,"n_samples_ran":8,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":8,"by_status":{"ran_honours":5,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":6},"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":"2607.22832","paper":"/paper/arxiv-2607-22832","title":"MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"sygkounas/MEMENTO","path":"MEMENTO/inference.py","file_url":"https://github.com/sygkounas/MEMENTO/blob/HEAD/MEMENTO/inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fa7c1ce1e0acb07b","mcp_get_code":{"code_sha256":"fa7c1ce1e0acb07b"}},{"arxiv_id":"2606.10321","paper":"/paper/arxiv-2606-10321","title":"Baseline-Free Policy Optimization for Neural Combinatorial Optimization","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"carsepmo/grpo-nco","path":"validate_checkpoints.py","file_url":"https://github.com/carsepmo/grpo-nco/blob/HEAD/validate_checkpoints.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"887a5f94b047dd9b","mcp_get_code":{"code_sha256":"887a5f94b047dd9b"}},{"arxiv_id":"2606.10187","paper":"/paper/arxiv-2606-10187","title":"Decision-Calibrated Conformal Uncertainty for Pacing Decisions in Streaming Advertising","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"p-shekhar/pacing-decisions-advertising","path":"src/pacing.py","file_url":"https://github.com/p-shekhar/pacing-decisions-advertising/blob/HEAD/src/pacing.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d3e1e851a080a450","mcp_get_code":{"code_sha256":"d3e1e851a080a450"}},{"arxiv_id":"2410.08979","paper":"/paper/overcoming-slow-decision-frequencies-in","title":"Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control","date":"2024-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dee0512/sequence-reinforcement-learning","path":"scripts/eval_sac.py","file_url":"https://github.com/dee0512/sequence-reinforcement-learning/blob/HEAD/scripts/eval_sac.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"54f3f957abc96d34","mcp_get_code":{"code_sha256":"54f3f957abc96d34"}},{"arxiv_id":"2409.04792","paper":"/paper/improving-deep-reinforcement-learning-by","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","date":"2024-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bluecontra/chain","path":"minatar/run_double_dqn_chain.py","file_url":"https://github.com/bluecontra/chain/blob/HEAD/minatar/run_double_dqn_chain.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"519bcb97d620e3bb","mcp_get_code":{"code_sha256":"519bcb97d620e3bb"}},{"arxiv_id":"2311.08384","paper":"/paper/offline-data-enhanced-on-policy-policy","title":"Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yifeizhou02/hnpg","path":"collect_offline.py","file_url":"https://github.com/yifeizhou02/hnpg/blob/HEAD/collect_offline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ff955a588d675fe2","mcp_get_code":{"code_sha256":"ff955a588d675fe2"}},{"arxiv_id":"2307.08875","paper":"/paper/natural-actor-critic-for-robust-reinforcement","title":"Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation","date":"2023-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tliu1997/rnac","path":"train_rnac.py","file_url":"https://github.com/tliu1997/rnac/blob/HEAD/train_rnac.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f74e37440bbe7726","mcp_get_code":{"code_sha256":"f74e37440bbe7726"}},{"arxiv_id":"2307.08875","paper":"/paper/natural-actor-critic-for-robust-reinforcement","title":"Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation","date":"2023-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tliu1997/rnac","path":"eval_rnac.py","file_url":"https://github.com/tliu1997/rnac/blob/HEAD/eval_rnac.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b49898d9bdfeb500","mcp_get_code":{"code_sha256":"b49898d9bdfeb500"}},{"arxiv_id":"2302.13348","paper":"/paper/kernel-conditional-moment-constraints-for","title":"Kernel Conditional Moment Constraints for Confounding Robust Inference","date":"2023-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kstoneriv3/confounding-robust-inference-old","path":"kcmc/data_binary.py","file_url":"https://github.com/kstoneriv3/confounding-robust-inference-old/blob/HEAD/kcmc/data_binary.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"212507fb5a1cb43c","mcp_get_code":{"code_sha256":"212507fb5a1cb43c"}},{"arxiv_id":"2302.13348","paper":"/paper/kernel-conditional-moment-constraints-for","title":"Kernel Conditional Moment Constraints for Confounding Robust Inference","date":"2023-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kstoneriv3/confounding-robust-inference-old","path":"kcmc/data_continuous.py","file_url":"https://github.com/kstoneriv3/confounding-robust-inference-old/blob/HEAD/kcmc/data_continuous.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"92802e330a871651","mcp_get_code":{"code_sha256":"92802e330a871651"}},{"arxiv_id":"1910.12179","paper":"/paper/bail-best-action-imitation-learning-for-batch-1","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","date":"2019-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lanyavik/BAIL","path":"spinup/spinup/algos/BAIL/main_static_bail.py","file_url":"https://github.com/lanyavik/BAIL/blob/HEAD/spinup/spinup/algos/BAIL/main_static_bail.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c74671448905c5d4","mcp_get_code":{"code_sha256":"c74671448905c5d4"}},{"arxiv_id":"1908.09357","paper":"/paper/dynamics-aware-embeddings","title":"Dynamics-aware Embeddings","date":"2019-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dyne-submission/dynamics-aware-embeddings","path":"rl/main_dyne.py","file_url":"https://github.com/dyne-submission/dynamics-aware-embeddings/blob/HEAD/rl/main_dyne.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a992966274227e22","mcp_get_code":{"code_sha256":"a992966274227e22"}},{"arxiv_id":"1805.09801","paper":"/paper/meta-gradient-reinforcement-learning","title":"Meta-Gradient Reinforcement Learning","date":"2018-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RobvanGastel/meta-rl-algorithms","path":"algos/rl2_ppo/learning.py","file_url":"https://github.com/RobvanGastel/meta-rl-algorithms/blob/HEAD/algos/rl2_ppo/learning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29d380560ab46818","mcp_get_code":{"code_sha256":"29d380560ab46818"}},{"arxiv_id":"1802.09477","paper":"/paper/addressing-function-approximation-error-in","title":"Addressing Function Approximation Error in Actor-Critic Methods","date":"2018-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VasaKiDD/TD3-deep-rl-research","path":"train/main_faimemory.py","file_url":"https://github.com/VasaKiDD/TD3-deep-rl-research/blob/HEAD/train/main_faimemory.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b0a2d4b21b2d48e6","mcp_get_code":{"code_sha256":"b0a2d4b21b2d48e6"}}]}