{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:W5LNMZKET3ICVPONRAJAEWDM2P","short_pith_number":"pith:W5LNMZKE","schema_version":"1.0","canonical_sha256":"b756d665449ed02abdcd881202586cd3fda6c901475dad9b19783ae77ce57959","source":{"kind":"arxiv","id":"2110.14248","version":2},"attestation_state":"computed","paper":{"title":"Learning Domain Invariant Representations in Goal-conditioned Block MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Beining Han, Chongyi Zheng, Harris Chan, Jimmy Ba, Keiran Paster, Michael R. Zhang","submitted_at":"2021-10-27T08:10:45Z","abstract_excerpt":"Deep Reinforcement Learning (RL) is successful in solving many complex Markov Decision Processes (MDPs) problems. However, agents often face unanticipated environmental changes after deployment in the real world. These changes are often spurious and unrelated to the underlying problem, such as background shifts for visual input agents. Unfortunately, deep RL policies are usually sensitive to these changes and fail to act robustly against them. This resembles the problem of domain generalization in supervised learning. In this work, we study this problem for goal-conditioned RL agents. We propo"},"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":"2110.14248","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T08:10:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3117b832b4f6119829071bc0a64ea196cc79e7cea1352f52f2cb034ecdbe0d5","abstract_canon_sha256":"75f8097536d3e66ad3f62a5e8bb294c0571d6478d2c84c499fbb9d6a35b8cb30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:45.540477Z","signature_b64":"UfsFVNkLn0Qayb8WNDhwWrbb8xLvve/13PLtvbWaWdXKMUV621wbTiUXfV5c26B8Zmjo/aPGqEBYAtq8C84ADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b756d665449ed02abdcd881202586cd3fda6c901475dad9b19783ae77ce57959","last_reissued_at":"2026-07-05T03:26:45.539920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:45.539920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Domain Invariant Representations in Goal-conditioned Block MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Beining Han, Chongyi Zheng, Harris Chan, Jimmy Ba, Keiran Paster, Michael R. Zhang","submitted_at":"2021-10-27T08:10:45Z","abstract_excerpt":"Deep Reinforcement Learning (RL) is successful in solving many complex Markov Decision Processes (MDPs) problems. However, agents often face unanticipated environmental changes after deployment in the real world. These changes are often spurious and unrelated to the underlying problem, such as background shifts for visual input agents. Unfortunately, deep RL policies are usually sensitive to these changes and fail to act robustly against them. This resembles the problem of domain generalization in supervised learning. In this work, we study this problem for goal-conditioned RL agents. We propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14248","kind":"arxiv","version":2},"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/2110.14248/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":"2110.14248","created_at":"2026-07-05T03:26:45.540001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.14248v2","created_at":"2026-07-05T03:26:45.540001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14248","created_at":"2026-07-05T03:26:45.540001+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5LNMZKET3IC","created_at":"2026-07-05T03:26:45.540001+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5LNMZKET3ICVPON","created_at":"2026-07-05T03:26:45.540001+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5LNMZKE","created_at":"2026-07-05T03:26:45.540001+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W5LNMZKET3ICVPONRAJAEWDM2P","json":"https://pith.science/pith/W5LNMZKET3ICVPONRAJAEWDM2P.json","graph_json":"https://pith.science/api/pith-number/W5LNMZKET3ICVPONRAJAEWDM2P/graph.json","events_json":"https://pith.science/api/pith-number/W5LNMZKET3ICVPONRAJAEWDM2P/events.json","paper":"https://pith.science/paper/W5LNMZKE"},"agent_actions":{"view_html":"https://pith.science/pith/W5LNMZKET3ICVPONRAJAEWDM2P","download_json":"https://pith.science/pith/W5LNMZKET3ICVPONRAJAEWDM2P.json","view_paper":"https://pith.science/paper/W5LNMZKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.14248&json=true","fetch_graph":"https://pith.science/api/pith-number/W5LNMZKET3ICVPONRAJAEWDM2P/graph.json","fetch_events":"https://pith.science/api/pith-number/W5LNMZKET3ICVPONRAJAEWDM2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5LNMZKET3ICVPONRAJAEWDM2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5LNMZKET3ICVPONRAJAEWDM2P/action/storage_attestation","attest_author":"https://pith.science/pith/W5LNMZKET3ICVPONRAJAEWDM2P/action/author_attestation","sign_citation":"https://pith.science/pith/W5LNMZKET3ICVPONRAJAEWDM2P/action/citation_signature","submit_replication":"https://pith.science/pith/W5LNMZKET3ICVPONRAJAEWDM2P/action/replication_record"}},"created_at":"2026-07-05T03:26:45.540001+00:00","updated_at":"2026-07-05T03:26:45.540001+00:00"}