{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OPEOVFHIPVPZFUHE3Q74EOLCBE","short_pith_number":"pith:OPEOVFHI","schema_version":"1.0","canonical_sha256":"73c8ea94e87d5f92d0e4dc3fc239620928b581389499b2d57a9671445321d5a3","source":{"kind":"arxiv","id":"2405.15369","version":1},"attestation_state":"computed","paper":{"title":"Cross-Domain Policy Adaptation by Capturing Representation Mismatch","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Jiafei Lyu, Jingwen Yang, Xiu Li, Zongqing Lu","submitted_at":"2024-05-24T09:06:12Z","abstract_excerpt":"It is vital to learn effective policies that can be transferred to different domains with dynamics discrepancies in reinforcement learning (RL). In this paper, we consider dynamics adaptation settings where there exists dynamics mismatch between the source domain and the target domain, and one can get access to sufficient source domain data, while can only have limited interactions with the target domain. Existing methods address this problem by learning domain classifiers, performing data filtering from a value discrepancy perspective, etc. Instead, we tackle this challenge from a decoupled r"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.15369","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T09:06:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"391c148a7c80801a5a08cfc0236faad736bf6bcaf015254768143336cdfc0f82","abstract_canon_sha256":"9e7bc818bd6deaae3703c47db062c051c846e0824d18538c57d8d015d45feeec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:48.569041Z","signature_b64":"Tv+bC+W3shKimQlEkjl+wR45/OTcPrnuI4wk135g39AFihmHO+MMIu9xKXgBquVVtm2Mwp/czGDIzEL4OmE2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73c8ea94e87d5f92d0e4dc3fc239620928b581389499b2d57a9671445321d5a3","last_reissued_at":"2026-07-05T08:22:48.568589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:48.568589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Domain Policy Adaptation by Capturing Representation Mismatch","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Jiafei Lyu, Jingwen Yang, Xiu Li, Zongqing Lu","submitted_at":"2024-05-24T09:06:12Z","abstract_excerpt":"It is vital to learn effective policies that can be transferred to different domains with dynamics discrepancies in reinforcement learning (RL). In this paper, we consider dynamics adaptation settings where there exists dynamics mismatch between the source domain and the target domain, and one can get access to sufficient source domain data, while can only have limited interactions with the target domain. Existing methods address this problem by learning domain classifiers, performing data filtering from a value discrepancy perspective, etc. Instead, we tackle this challenge from a decoupled r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15369","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.15369/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.15369","created_at":"2026-07-05T08:22:48.568660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15369v1","created_at":"2026-07-05T08:22:48.568660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15369","created_at":"2026-07-05T08:22:48.568660+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPEOVFHIPVPZ","created_at":"2026-07-05T08:22:48.568660+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPEOVFHIPVPZFUHE","created_at":"2026-07-05T08:22:48.568660+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPEOVFHI","created_at":"2026-07-05T08:22:48.568660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24862","citing_title":"Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24810","citing_title":"Cross-Domain Energy-Guided Diffusion Generation for Off-Dynamics Reinforcement Learning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13054","citing_title":"Bridging Domain Gaps with Target-Aligned Generation for Offline Reinforcement Learning","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OPEOVFHIPVPZFUHE3Q74EOLCBE","json":"https://pith.science/pith/OPEOVFHIPVPZFUHE3Q74EOLCBE.json","graph_json":"https://pith.science/api/pith-number/OPEOVFHIPVPZFUHE3Q74EOLCBE/graph.json","events_json":"https://pith.science/api/pith-number/OPEOVFHIPVPZFUHE3Q74EOLCBE/events.json","paper":"https://pith.science/paper/OPEOVFHI"},"agent_actions":{"view_html":"https://pith.science/pith/OPEOVFHIPVPZFUHE3Q74EOLCBE","download_json":"https://pith.science/pith/OPEOVFHIPVPZFUHE3Q74EOLCBE.json","view_paper":"https://pith.science/paper/OPEOVFHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15369&json=true","fetch_graph":"https://pith.science/api/pith-number/OPEOVFHIPVPZFUHE3Q74EOLCBE/graph.json","fetch_events":"https://pith.science/api/pith-number/OPEOVFHIPVPZFUHE3Q74EOLCBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPEOVFHIPVPZFUHE3Q74EOLCBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPEOVFHIPVPZFUHE3Q74EOLCBE/action/storage_attestation","attest_author":"https://pith.science/pith/OPEOVFHIPVPZFUHE3Q74EOLCBE/action/author_attestation","sign_citation":"https://pith.science/pith/OPEOVFHIPVPZFUHE3Q74EOLCBE/action/citation_signature","submit_replication":"https://pith.science/pith/OPEOVFHIPVPZFUHE3Q74EOLCBE/action/replication_record"}},"created_at":"2026-07-05T08:22:48.568660+00:00","updated_at":"2026-07-05T08:22:48.568660+00:00"}