{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WESWFSLJL6GWVKUJXKMSM3OEHL","short_pith_number":"pith:WESWFSLJ","schema_version":"1.0","canonical_sha256":"b12562c9695f8d6aaa89ba99266dc43af7575bf4604a6fc561d8de1c08807c98","source":{"kind":"arxiv","id":"2110.05169","version":3},"attestation_state":"computed","paper":{"title":"Learning a subspace of policies for online adaptation in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jean-Baptiste Gaya, Laure Soulier, Ludovic Denoyer","submitted_at":"2021-10-11T11:43:34Z","abstract_excerpt":"Deep Reinforcement Learning (RL) is mainly studied in a setting where the training and the testing environments are similar. But in many practical applications, these environments may differ. For instance, in control systems, the robot(s) on which a policy is learned might differ from the robot(s) on which a policy will run. It can be caused by different internal factors (e.g., calibration issues, system attrition, defective modules) or also by external changes (e.g., weather conditions). There is a need to develop RL methods that generalize well to variations of the training conditions. In th"},"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":"2110.05169","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T11:43:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10606e872c016a569a708601c8b4aeffe53997d0dfcfb6c6fdfee469e6d4d613","abstract_canon_sha256":"3c07b8761ac31b5f2f46b8632198c39d64ffc96c8ee05ce7dad3704567cee346"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:13.238955Z","signature_b64":"fMI2RH6crREeE47hE0Qzkr1lufdWBHNwqE1zCVPshMYsVhJLteVJUvvOHFPTbkoqN+vgorsYP6EdlSJh3blCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b12562c9695f8d6aaa89ba99266dc43af7575bf4604a6fc561d8de1c08807c98","last_reissued_at":"2026-07-05T05:09:13.238524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:13.238524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a subspace of policies for online adaptation in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jean-Baptiste Gaya, Laure Soulier, Ludovic Denoyer","submitted_at":"2021-10-11T11:43:34Z","abstract_excerpt":"Deep Reinforcement Learning (RL) is mainly studied in a setting where the training and the testing environments are similar. But in many practical applications, these environments may differ. For instance, in control systems, the robot(s) on which a policy is learned might differ from the robot(s) on which a policy will run. It can be caused by different internal factors (e.g., calibration issues, system attrition, defective modules) or also by external changes (e.g., weather conditions). There is a need to develop RL methods that generalize well to variations of the training conditions. In th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05169","kind":"arxiv","version":3},"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/2110.05169/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":"2110.05169","created_at":"2026-07-05T05:09:13.238580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.05169v3","created_at":"2026-07-05T05:09:13.238580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05169","created_at":"2026-07-05T05:09:13.238580+00:00"},{"alias_kind":"pith_short_12","alias_value":"WESWFSLJL6GW","created_at":"2026-07-05T05:09:13.238580+00:00"},{"alias_kind":"pith_short_16","alias_value":"WESWFSLJL6GWVKUJ","created_at":"2026-07-05T05:09:13.238580+00:00"},{"alias_kind":"pith_short_8","alias_value":"WESWFSLJ","created_at":"2026-07-05T05:09:13.238580+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/WESWFSLJL6GWVKUJXKMSM3OEHL","json":"https://pith.science/pith/WESWFSLJL6GWVKUJXKMSM3OEHL.json","graph_json":"https://pith.science/api/pith-number/WESWFSLJL6GWVKUJXKMSM3OEHL/graph.json","events_json":"https://pith.science/api/pith-number/WESWFSLJL6GWVKUJXKMSM3OEHL/events.json","paper":"https://pith.science/paper/WESWFSLJ"},"agent_actions":{"view_html":"https://pith.science/pith/WESWFSLJL6GWVKUJXKMSM3OEHL","download_json":"https://pith.science/pith/WESWFSLJL6GWVKUJXKMSM3OEHL.json","view_paper":"https://pith.science/paper/WESWFSLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.05169&json=true","fetch_graph":"https://pith.science/api/pith-number/WESWFSLJL6GWVKUJXKMSM3OEHL/graph.json","fetch_events":"https://pith.science/api/pith-number/WESWFSLJL6GWVKUJXKMSM3OEHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WESWFSLJL6GWVKUJXKMSM3OEHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WESWFSLJL6GWVKUJXKMSM3OEHL/action/storage_attestation","attest_author":"https://pith.science/pith/WESWFSLJL6GWVKUJXKMSM3OEHL/action/author_attestation","sign_citation":"https://pith.science/pith/WESWFSLJL6GWVKUJXKMSM3OEHL/action/citation_signature","submit_replication":"https://pith.science/pith/WESWFSLJL6GWVKUJXKMSM3OEHL/action/replication_record"}},"created_at":"2026-07-05T05:09:13.238580+00:00","updated_at":"2026-07-05T05:09:13.238580+00:00"}