{"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":"/paper/collaborative-world-models-an-online-offline","title":"Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning","arxiv_id":"2305.15260","date":"2023-05-24","proceeding":null,"authors":["Qi Wang","Junming Yang","Yunbo Wang","Xin Jin","Wenjun Zeng","Xiaokang Yang"],"abstract":"Training offline RL models using visual inputs poses two significant challenges, i.e., the overfitting problem in representation learning and the overestimation bias for expected future rewards. Recent work has attempted to alleviate the overestimation bias by encouraging conservative behaviors. This paper, in contrast, tries to build more flexible constraints for value estimation without impeding the exploration of potential advantages. The key idea is to leverage off-the-shelf RL simulators, which can be easily interacted with in an online manner, as the \"test bed\" for offline policies. To enable effective online-to-offline knowledge transfer, we introduce CoWorld, a model-based RL approach that mitigates cross-domain discrepancies in state and reward spaces. Experimental results demonstrate the effectiveness of CoWorld, outperforming existing RL approaches by large margins.","url_abs":"https://arxiv.org/abs/2305.15260v4","url_pdf":"https://arxiv.org/pdf/2305.15260v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"collaborative-world-models-an-online-offline","repo_url":"https://github.com/qiwang067/CoWorld","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.15260","atlas_url":"https://app.syntology.ai/?focus=2305.15260","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15260"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qiwang067/CoWorld","reach":null}],"summary":{"ran":9,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":13,"ran":10,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":13,"samples":[{"code_sha256_prefix":"44e6fedc5e22071c","entry":"Bernoulli","repo":"qiwang067/CoWorld","repo_kind":"official","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44e6fedc5e22071c"}},{"code_sha256_prefix":"bd7d95ae3f97198e","entry":"ContDist","repo":"qiwang067/CoWorld","repo_kind":"official","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bd7d95ae3f97198e"}},{"code_sha256_prefix":"f8adc38d14492b89","entry":"ConvDecoder","repo":"qiwang067/CoWorld","repo_kind":"official","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f8adc38d14492b89"}},{"code_sha256_prefix":"7ca1f7001da75dd7","entry":"ConvEncoder","repo":"qiwang067/CoWorld","repo_kind":"official","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7ca1f7001da75dd7"}},{"code_sha256_prefix":"62aa6257afaf0318","entry":"DenseHead","repo":"qiwang067/CoWorld","repo_kind":"official","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"62aa6257afaf0318"}},{"code_sha256_prefix":"c2956715777b32f9","entry":"GRUCell","repo":"qiwang067/CoWorld","repo_kind":"official","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c2956715777b32f9"}},{"code_sha256_prefix":"6a87a463d6fbba12","entry":"OneHotDist","repo":"qiwang067/CoWorld","repo_kind":"official","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6a87a463d6fbba12"}},{"code_sha256_prefix":"47e0a0e2a2c2db4b","entry":"Optimizer","repo":"qiwang067/CoWorld","repo_kind":"official","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"47e0a0e2a2c2db4b"}},{"code_sha256_prefix":"2445794b39372705","entry":"UnnormalizedHuber","repo":"qiwang067/CoWorld","repo_kind":"official","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2445794b39372705"}},{"code_sha256_prefix":"02b17681a370b688","entry":"schedule","repo":"qiwang067/CoWorld","repo_kind":"official","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"02b17681a370b688"}},{"code_sha256_prefix":"03954e42255f0941","entry":"RSSM","repo":"qiwang067/CoWorld","repo_kind":"official","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"03954e42255f0941"}},{"code_sha256_prefix":"2c89a891f4485238","entry":"WorldModel","repo":"qiwang067/CoWorld","repo_kind":"official","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2c89a891f4485238"}},{"code_sha256_prefix":"514d05952ec692b5","entry":"static_scan","repo":"qiwang067/CoWorld","repo_kind":"official","path":"models.py","file_url":"https://github.com/qiwang067/CoWorld/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"514d05952ec692b5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}