{"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/td-target","entry":"td_target","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":11,"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":3,"n_samples_ran":3,"n_samples_fingerprinted":2,"n_places":11,"n_places_pointer_only":2,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2402.06819","paper":"/paper/monitored-markov-decision-processes","title":"Monitored Markov Decision Processes","date":"2024-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amiithinks/mon_mdp_aamas24","path":"src/critic.py","file_url":"https://github.com/amiithinks/mon_mdp_aamas24/blob/HEAD/src/critic.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ff95638173fd5d86","mcp_get_code":{"code_sha256":"ff95638173fd5d86"}},{"arxiv_id":"2309.08571","paper":"/paper/a-bayesian-approach-to-robust-inverse","title":"A Bayesian Approach to Robust Inverse Reinforcement Learning","date":"2023-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ran-weii/bmirl_tf","path":"rambo/algorithms/birl.py","file_url":"https://github.com/ran-weii/bmirl_tf/blob/HEAD/rambo/algorithms/birl.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6785bf48d01be235","mcp_get_code":{"code_sha256":"6785bf48d01be235"}},{"arxiv_id":"2212.00124","paper":"/paper/one-risk-to-rule-them-all-a-risk-sensitive-1","title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning","date":"2022-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"marc-rigter/1R2R","path":"_1R2R/algorithms/_1R2R.py","file_url":"https://github.com/marc-rigter/1R2R/blob/HEAD/_1R2R/algorithms/_1R2R.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31deb9c7be58e00c","mcp_get_code":{"code_sha256":"31deb9c7be58e00c"}},{"arxiv_id":"2204.12581","paper":"/paper/rambo-rl-robust-adversarial-model-based","title":"RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning","date":"2022-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"marc-rigter/rambo","path":"rambo/algorithms/rambo.py","file_url":"https://github.com/marc-rigter/rambo/blob/HEAD/rambo/algorithms/rambo.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31deb9c7be58e00c","mcp_get_code":{"code_sha256":"31deb9c7be58e00c"}},{"arxiv_id":"2103.13842","paper":"/paper/model-predictive-actor-critic-accelerating","title":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","date":"2021-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dnandha/mopac","path":"mopac/algorithms/mopac.py","file_url":"https://github.com/dnandha/mopac/blob/HEAD/mopac/algorithms/mopac.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31deb9c7be58e00c","mcp_get_code":{"code_sha256":"31deb9c7be58e00c"}},{"arxiv_id":"2010.09546","paper":"/paper/model-based-policy-optimization-with","title":"Model-based Policy Optimization with Unsupervised Model Adaptation","date":"2020-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RockySJ/ampo","path":"ampo.py","file_url":"https://github.com/RockySJ/ampo/blob/HEAD/ampo.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31deb9c7be58e00c","mcp_get_code":{"code_sha256":"31deb9c7be58e00c"}},{"arxiv_id":"2007.01995","paper":"/paper/bidirectional-model-based-policy-optimization","title":"Bidirectional Model-based Policy Optimization","date":"2020-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanglai/bmpo","path":"bmpo.py","file_url":"https://github.com/hanglai/bmpo/blob/HEAD/bmpo.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31deb9c7be58e00c","mcp_get_code":{"code_sha256":"31deb9c7be58e00c"}},{"arxiv_id":"2006.13916","paper":"/paper/off-dynamics-reinforcement-learning-training","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","date":"2020-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JannerM/mbpo","path":"mbpo/algorithms/mbpo.py","file_url":"https://github.com/JannerM/mbpo/blob/HEAD/mbpo/algorithms/mbpo.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31deb9c7be58e00c","mcp_get_code":{"code_sha256":"31deb9c7be58e00c"}},{"arxiv_id":"1906.08253","paper":"/paper/when-to-trust-your-model-model-based-policy","title":"When to Trust Your Model: Model-Based Policy Optimization","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"31deb9c7be58e00c","mcp_get_code":{"code_sha256":"31deb9c7be58e00c"}},{"arxiv_id":"1812.05905","paper":"/paper/soft-actor-critic-algorithms-and-applications","title":"Soft Actor-Critic Algorithms and Applications","date":"2018-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"31deb9c7be58e00c","mcp_get_code":{"code_sha256":"31deb9c7be58e00c"}},{"arxiv_id":"1703.03400","paper":"/paper/model-agnostic-meta-learning-for-fast","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","date":"2017-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iclavera/meta-mb","path":"meta_mb/algos/sac.py","file_url":"https://github.com/iclavera/meta-mb/blob/HEAD/meta_mb/algos/sac.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31deb9c7be58e00c","mcp_get_code":{"code_sha256":"31deb9c7be58e00c"}}]}