{"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/rssm","entry":"RSSM","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":7,"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":10,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"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":"2603.18202","paper":"/paper/arxiv-2603-18202","title":"R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"NM512/r2dreamer","path":"dreamer.py","file_url":"https://github.com/NM512/r2dreamer/blob/HEAD/dreamer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c96d50956593ba0a","mcp_get_code":{"code_sha256":"c96d50956593ba0a"}},{"arxiv_id":"2312.02019","paper":"/paper/action-inference-by-maximising-evidence-zero-1","title":"Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"argmax-ai/aime","path":"aime/models/ssm.py","file_url":"https://github.com/argmax-ai/aime/blob/HEAD/aime/models/ssm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"518be015fb96eae9","mcp_get_code":{"code_sha256":"518be015fb96eae9"}},{"arxiv_id":"2305.15260","paper":"/paper/collaborative-world-models-an-online-offline","title":"Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qiwang067/CoWorld","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"03954e42255f0941","mcp_get_code":{"code_sha256":"03954e42255f0941"}},{"arxiv_id":"2301.04104","paper":"/paper/mastering-diverse-domains-through-world","title":"Mastering Diverse Domains through World Models","date":"2023-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nm512/dreamerv3-torch","path":"dreamer.py","file_url":"https://github.com/nm512/dreamerv3-torch/blob/HEAD/dreamer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"795c1fe9da508672","mcp_get_code":{"code_sha256":"795c1fe9da508672"}},{"arxiv_id":"2210.07729","paper":"/paper/model-based-imitation-learning-for-urban","title":"Model-Based Imitation Learning for Urban Driving","date":"2022-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wayveai/mile","path":"mile/models/mile.py","file_url":"https://github.com/wayveai/mile/blob/HEAD/mile/models/mile.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"86c73d56030a9b3b","mcp_get_code":{"code_sha256":"86c73d56030a9b3b"}},{"arxiv_id":"2010.02193","paper":"/paper/mastering-atari-with-discrete-world-models-1","title":"Mastering Atari with Discrete World Models","date":"2020-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RajGhugare19/dreamerv2","path":"dreamerv2/models/rssm.py","file_url":"https://github.com/RajGhugare19/dreamerv2/blob/HEAD/dreamerv2/models/rssm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"11fa7e68493b760d","mcp_get_code":{"code_sha256":"11fa7e68493b760d"}},{"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":"chamorajg/pl-dreamer","path":"planet.py","file_url":"https://github.com/chamorajg/pl-dreamer/blob/HEAD/planet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5fd2e204f8b1686c","mcp_get_code":{"code_sha256":"5fd2e204f8b1686c"}},{"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":"zhixuan-lin/dreamer-pytorch","path":"dreamer.py","file_url":"https://github.com/zhixuan-lin/dreamer-pytorch/blob/HEAD/dreamer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d0fb3df4884ed3da","mcp_get_code":{"code_sha256":"d0fb3df4884ed3da"}},{"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":"adityabingi/Dreamer","path":"dreamer.py","file_url":"https://github.com/adityabingi/Dreamer/blob/HEAD/dreamer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6ed93a3bd0b35bbd","mcp_get_code":{"code_sha256":"6ed93a3bd0b35bbd"}},{"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":"Eclectic-Sheep/sheeprl","path":"sheeprl/algos/dreamer_v1/agent.py","file_url":"https://github.com/Eclectic-Sheep/sheeprl/blob/HEAD/sheeprl/algos/dreamer_v1/agent.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":"6f6fbb1df0959d34","mcp_get_code":{"code_sha256":"6f6fbb1df0959d34"}}]}