{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SBL3347KUIJYUN36XZ7R2JATO7","short_pith_number":"pith:SBL3347K","schema_version":"1.0","canonical_sha256":"9057bdf3eaa2138a377ebe7f1d241377d45c95febc0fd848ea93610a92a0fd4c","source":{"kind":"arxiv","id":"2506.13690","version":1},"attestation_state":"computed","paper":{"title":"Meta-learning how to Share Credit among Macro-Actions","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ionel-Alexandru Hosu, Razvan Pascanu, Traian Rebedea","submitted_at":"2025-06-16T16:52:49Z","abstract_excerpt":"One proposed mechanism to improve exploration in reinforcement learning is through the use of macro-actions. Paradoxically though, in many scenarios the naive addition of macro-actions does not lead to better exploration, but rather the opposite. It has been argued that this was caused by adding non-useful macros and multiple works have focused on mechanisms to discover effectively environment-specific useful macros. In this work, we take a slightly different perspective. We argue that the difficulty stems from the trade-offs between reducing the average number of decisions per episode versus "},"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":"2506.13690","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-16T16:52:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d23fedc2ccd7682717503226194f6de96238223ef95f37881339fa767478e55b","abstract_canon_sha256":"0cf8b9180abb7e263cf61501e78e151b9f6251aad0062ad548c96a75c918a58c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:24.929202Z","signature_b64":"WFldKIZHpfkBIG+E39z7Wl7F/clZSZ17ipwyjalDfZ9F29uWOFexn+RUBeg7O7SEUGkjMF0oXl6r30b7tIEECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9057bdf3eaa2138a377ebe7f1d241377d45c95febc0fd848ea93610a92a0fd4c","last_reissued_at":"2026-07-05T11:22:24.928645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:24.928645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-learning how to Share Credit among Macro-Actions","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ionel-Alexandru Hosu, Razvan Pascanu, Traian Rebedea","submitted_at":"2025-06-16T16:52:49Z","abstract_excerpt":"One proposed mechanism to improve exploration in reinforcement learning is through the use of macro-actions. Paradoxically though, in many scenarios the naive addition of macro-actions does not lead to better exploration, but rather the opposite. It has been argued that this was caused by adding non-useful macros and multiple works have focused on mechanisms to discover effectively environment-specific useful macros. In this work, we take a slightly different perspective. We argue that the difficulty stems from the trade-offs between reducing the average number of decisions per episode versus "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13690","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/2506.13690/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":"2506.13690","created_at":"2026-07-05T11:22:24.928706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13690v1","created_at":"2026-07-05T11:22:24.928706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13690","created_at":"2026-07-05T11:22:24.928706+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBL3347KUIJY","created_at":"2026-07-05T11:22:24.928706+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBL3347KUIJYUN36","created_at":"2026-07-05T11:22:24.928706+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBL3347K","created_at":"2026-07-05T11:22:24.928706+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/SBL3347KUIJYUN36XZ7R2JATO7","json":"https://pith.science/pith/SBL3347KUIJYUN36XZ7R2JATO7.json","graph_json":"https://pith.science/api/pith-number/SBL3347KUIJYUN36XZ7R2JATO7/graph.json","events_json":"https://pith.science/api/pith-number/SBL3347KUIJYUN36XZ7R2JATO7/events.json","paper":"https://pith.science/paper/SBL3347K"},"agent_actions":{"view_html":"https://pith.science/pith/SBL3347KUIJYUN36XZ7R2JATO7","download_json":"https://pith.science/pith/SBL3347KUIJYUN36XZ7R2JATO7.json","view_paper":"https://pith.science/paper/SBL3347K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13690&json=true","fetch_graph":"https://pith.science/api/pith-number/SBL3347KUIJYUN36XZ7R2JATO7/graph.json","fetch_events":"https://pith.science/api/pith-number/SBL3347KUIJYUN36XZ7R2JATO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBL3347KUIJYUN36XZ7R2JATO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBL3347KUIJYUN36XZ7R2JATO7/action/storage_attestation","attest_author":"https://pith.science/pith/SBL3347KUIJYUN36XZ7R2JATO7/action/author_attestation","sign_citation":"https://pith.science/pith/SBL3347KUIJYUN36XZ7R2JATO7/action/citation_signature","submit_replication":"https://pith.science/pith/SBL3347KUIJYUN36XZ7R2JATO7/action/replication_record"}},"created_at":"2026-07-05T11:22:24.928706+00:00","updated_at":"2026-07-05T11:22:24.928706+00:00"}