{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CDXN3KOFKHHAO5GHZ3TLRXEFEX","short_pith_number":"pith:CDXN3KOF","schema_version":"1.0","canonical_sha256":"10eedda9c551ce0774c7cee6b8dc8525c037c5e199941431fa0b228381d46c16","source":{"kind":"arxiv","id":"2308.01759","version":1},"attestation_state":"computed","paper":{"title":"Bag of Policies for Distributional Deep Exploration","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aldo Faisal, Asen Nachkov, Filippo Valdettaro, Giulia Luise, Luchen Li","submitted_at":"2023-08-03T13:43:03Z","abstract_excerpt":"Efficient exploration in complex environments remains a major challenge for reinforcement learning (RL). Compared to previous Thompson sampling-inspired mechanisms that enable temporally extended exploration, i.e., deep exploration, we focus on deep exploration in distributional RL. We develop here a general purpose approach, Bag of Policies (BoP), that can be built on top of any return distribution estimator by maintaining a population of its copies. BoP consists of an ensemble of multiple heads that are updated independently. During training, each episode is controlled by only one of the hea"},"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":"2308.01759","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T13:43:03Z","cross_cats_sorted":[],"title_canon_sha256":"d244995c7fe037aab4660898b9a57c4b0a36dcfc3a0b170de7eab99dab4dc520","abstract_canon_sha256":"eb4306ac6474c1eeaa561e2db42df52d56b680a6db1721847ac4fdbce8f6435e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:22.831448Z","signature_b64":"KHUP4awXkZKnD3V999lb0bnHOVioA+eFePl+IZb2SptANslkeKEKkVur4Xshg0q+pg5md/nsma3Wi8NXFw8sDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10eedda9c551ce0774c7cee6b8dc8525c037c5e199941431fa0b228381d46c16","last_reissued_at":"2026-07-05T06:37:22.830970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:22.830970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bag of Policies for Distributional Deep Exploration","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aldo Faisal, Asen Nachkov, Filippo Valdettaro, Giulia Luise, Luchen Li","submitted_at":"2023-08-03T13:43:03Z","abstract_excerpt":"Efficient exploration in complex environments remains a major challenge for reinforcement learning (RL). Compared to previous Thompson sampling-inspired mechanisms that enable temporally extended exploration, i.e., deep exploration, we focus on deep exploration in distributional RL. We develop here a general purpose approach, Bag of Policies (BoP), that can be built on top of any return distribution estimator by maintaining a population of its copies. BoP consists of an ensemble of multiple heads that are updated independently. During training, each episode is controlled by only one of the hea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01759","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/2308.01759/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":"2308.01759","created_at":"2026-07-05T06:37:22.831030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.01759v1","created_at":"2026-07-05T06:37:22.831030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01759","created_at":"2026-07-05T06:37:22.831030+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDXN3KOFKHHA","created_at":"2026-07-05T06:37:22.831030+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDXN3KOFKHHAO5GH","created_at":"2026-07-05T06:37:22.831030+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDXN3KOF","created_at":"2026-07-05T06:37:22.831030+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/CDXN3KOFKHHAO5GHZ3TLRXEFEX","json":"https://pith.science/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX.json","graph_json":"https://pith.science/api/pith-number/CDXN3KOFKHHAO5GHZ3TLRXEFEX/graph.json","events_json":"https://pith.science/api/pith-number/CDXN3KOFKHHAO5GHZ3TLRXEFEX/events.json","paper":"https://pith.science/paper/CDXN3KOF"},"agent_actions":{"view_html":"https://pith.science/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX","download_json":"https://pith.science/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX.json","view_paper":"https://pith.science/paper/CDXN3KOF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.01759&json=true","fetch_graph":"https://pith.science/api/pith-number/CDXN3KOFKHHAO5GHZ3TLRXEFEX/graph.json","fetch_events":"https://pith.science/api/pith-number/CDXN3KOFKHHAO5GHZ3TLRXEFEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX/action/storage_attestation","attest_author":"https://pith.science/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX/action/author_attestation","sign_citation":"https://pith.science/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX/action/citation_signature","submit_replication":"https://pith.science/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX/action/replication_record"}},"created_at":"2026-07-05T06:37:22.831030+00:00","updated_at":"2026-07-05T06:37:22.831030+00:00"}