{"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/transitionmodel","entry":"TransitionModel","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":5,"n_papers_ran":4,"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":8,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":4},"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":"2505.16732","paper":"/paper/sequential-monte-carlo-for-policy","title":"Sequential Monte Carlo for Policy Optimization in Continuous POMDPs","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Sahel13/particle-pomdp","path":"ppomdp/smc/_smc.py","file_url":"https://github.com/Sahel13/particle-pomdp/blob/HEAD/ppomdp/smc/_smc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fbce0b9594a13a87","mcp_get_code":{"code_sha256":"fbce0b9594a13a87"}},{"arxiv_id":"2201.12096","paper":"/paper/mask-based-latent-reconstruction-for","title":"Mask-based Latent Reconstruction for Reinforcement Learning","date":"2022-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/Playvirtual","path":"Atari/src/models.py","file_url":"https://github.com/microsoft/Playvirtual/blob/HEAD/Atari/src/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f9e622f31f261cbe","mcp_get_code":{"code_sha256":"f9e622f31f261cbe"}},{"arxiv_id":"2005.05960","paper":"/paper/planning-to-explore-via-self-supervised-world","title":"Planning to Explore via Self-Supervised World Models","date":"2020-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yusukeurakami/plan2explore-pytorch","path":"models.py","file_url":"https://github.com/yusukeurakami/plan2explore-pytorch/blob/HEAD/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"916814eea2a6e02e","mcp_get_code":{"code_sha256":"916814eea2a6e02e"}},{"arxiv_id":"1912.01603","paper":"/paper/dream-to-control-learning-behaviors-by-latent","title":"Dream to Control: Learning Behaviors by Latent Imagination","date":"2019-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yizhao111/dreamer-pytorch","path":"agent.py","file_url":"https://github.com/Yizhao111/dreamer-pytorch/blob/HEAD/agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2a61bebe2088ddb9","mcp_get_code":{"code_sha256":"2a61bebe2088ddb9"}},{"arxiv_id":"1912.01603","paper":"/paper/dream-to-control-learning-behaviors-by-latent","title":"Dream to Control: Learning Behaviors by Latent Imagination","date":"2019-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yusukeurakami/dreamer-pytorch","path":"models.py","file_url":"https://github.com/yusukeurakami/dreamer-pytorch/blob/HEAD/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"28f50a7941b7cc60","mcp_get_code":{"code_sha256":"28f50a7941b7cc60"}},{"arxiv_id":"1811.04551","paper":"/paper/learning-latent-dynamics-for-planning-from","title":"Learning Latent Dynamics for Planning from Pixels","date":"2018-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xingyu-lin/softagent","path":"planet/models.py","file_url":"https://github.com/xingyu-lin/softagent/blob/HEAD/planet/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"efe7f713034a1846","mcp_get_code":{"code_sha256":"efe7f713034a1846"}},{"arxiv_id":"1811.04551","paper":"/paper/learning-latent-dynamics-for-planning-from","title":"Learning Latent Dynamics for Planning from Pixels","date":"2018-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kaixhin/PlaNet","path":"models.py","file_url":"https://github.com/Kaixhin/PlaNet/blob/HEAD/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2d4d65f835c80d5","mcp_get_code":{"code_sha256":"c2d4d65f835c80d5"}},{"arxiv_id":"1811.04551","paper":"/paper/learning-latent-dynamics-for-planning-from","title":"Learning Latent Dynamics for Planning from Pixels","date":"2018-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yizhao111/dreamer-pytorch","path":"models.py","file_url":"https://github.com/Yizhao111/dreamer-pytorch/blob/HEAD/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2cbf0fc5d0dc1a5","mcp_get_code":{"code_sha256":"c2cbf0fc5d0dc1a5"}}]}