{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CDXN3KOFKHHAO5GHZ3TLRXEFEX","short_pith_number":"pith:CDXN3KOF","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"},"canonical_sha256":"10eedda9c551ce0774c7cee6b8dc8525c037c5e199941431fa0b228381d46c16","source":{"kind":"arxiv","id":"2308.01759","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.01759","created_at":"2026-07-05T06:37:22Z"},{"alias_kind":"arxiv_version","alias_value":"2308.01759v1","created_at":"2026-07-05T06:37:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01759","created_at":"2026-07-05T06:37:22Z"},{"alias_kind":"pith_short_12","alias_value":"CDXN3KOFKHHA","created_at":"2026-07-05T06:37:22Z"},{"alias_kind":"pith_short_16","alias_value":"CDXN3KOFKHHAO5GH","created_at":"2026-07-05T06:37:22Z"},{"alias_kind":"pith_short_8","alias_value":"CDXN3KOF","created_at":"2026-07-05T06:37:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CDXN3KOFKHHAO5GHZ3TLRXEFEX","target":"record","payload":{"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"},"canonical_sha256":"10eedda9c551ce0774c7cee6b8dc8525c037c5e199941431fa0b228381d46c16","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"},"source_kind":"arxiv","source_id":"2308.01759","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:37:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cnMmoqk09HGzla3PciT/2/h48MMJeVOixuo14K2HtyyazaBnxy90eN0HRIXMqxXDHBb20S6qwoi/focqjlvDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:20:56.698023Z"},"content_sha256":"7ecc7609817d9d7b7e857e9e874eac853ccab282306890f68b1f1ed843a421ef","schema_version":"1.0","event_id":"sha256:7ecc7609817d9d7b7e857e9e874eac853ccab282306890f68b1f1ed843a421ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CDXN3KOFKHHAO5GHZ3TLRXEFEX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:37:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NuADhD2akbgtzZcdJBxVRSGj8MUM0DWDM1cI7+5Zc/LhUJxe7/gKtmNRTrUh4Dp26QK7TsF7PBu7ARqZ83knAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:20:56.698401Z"},"content_sha256":"7e7d214889b2e427a8355e92c8c1d34d9288d95cc75ab863753c17f1b66529bc","schema_version":"1.0","event_id":"sha256:7e7d214889b2e427a8355e92c8c1d34d9288d95cc75ab863753c17f1b66529bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX/bundle.json","state_url":"https://pith.science/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T23:20:56Z","links":{"resolver":"https://pith.science/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX","bundle":"https://pith.science/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX/bundle.json","state":"https://pith.science/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CDXN3KOFKHHAO5GHZ3TLRXEFEX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CDXN3KOFKHHAO5GHZ3TLRXEFEX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"eb4306ac6474c1eeaa561e2db42df52d56b680a6db1721847ac4fdbce8f6435e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T13:43:03Z","title_canon_sha256":"d244995c7fe037aab4660898b9a57c4b0a36dcfc3a0b170de7eab99dab4dc520"},"schema_version":"1.0","source":{"id":"2308.01759","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.01759","created_at":"2026-07-05T06:37:22Z"},{"alias_kind":"arxiv_version","alias_value":"2308.01759v1","created_at":"2026-07-05T06:37:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01759","created_at":"2026-07-05T06:37:22Z"},{"alias_kind":"pith_short_12","alias_value":"CDXN3KOFKHHA","created_at":"2026-07-05T06:37:22Z"},{"alias_kind":"pith_short_16","alias_value":"CDXN3KOFKHHAO5GH","created_at":"2026-07-05T06:37:22Z"},{"alias_kind":"pith_short_8","alias_value":"CDXN3KOF","created_at":"2026-07-05T06:37:22Z"}],"graph_snapshots":[{"event_id":"sha256:7e7d214889b2e427a8355e92c8c1d34d9288d95cc75ab863753c17f1b66529bc","target":"graph","created_at":"2026-07-05T06:37:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.01759/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aldo Faisal, Asen Nachkov, Filippo Valdettaro, Giulia Luise, Luchen Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T13:43:03Z","title":"Bag of Policies for Distributional Deep Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01759","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7ecc7609817d9d7b7e857e9e874eac853ccab282306890f68b1f1ed843a421ef","target":"record","created_at":"2026-07-05T06:37:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"eb4306ac6474c1eeaa561e2db42df52d56b680a6db1721847ac4fdbce8f6435e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T13:43:03Z","title_canon_sha256":"d244995c7fe037aab4660898b9a57c4b0a36dcfc3a0b170de7eab99dab4dc520"},"schema_version":"1.0","source":{"id":"2308.01759","kind":"arxiv","version":1}},"canonical_sha256":"10eedda9c551ce0774c7cee6b8dc8525c037c5e199941431fa0b228381d46c16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10eedda9c551ce0774c7cee6b8dc8525c037c5e199941431fa0b228381d46c16","first_computed_at":"2026-07-05T06:37:22.830970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:37:22.830970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KHUP4awXkZKnD3V999lb0bnHOVioA+eFePl+IZb2SptANslkeKEKkVur4Xshg0q+pg5md/nsma3Wi8NXFw8sDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:37:22.831448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.01759","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ecc7609817d9d7b7e857e9e874eac853ccab282306890f68b1f1ed843a421ef","sha256:7e7d214889b2e427a8355e92c8c1d34d9288d95cc75ab863753c17f1b66529bc"],"state_sha256":"9e052c8510fd982765c5221a28ec17650c28dce8b67454c17793b139a63af911"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5/9U0wiQopdRewaWTEn/vU3iH6LS/yZiHhCimL3wa4iZjQF2ila46+tQ13oOYqSlHSePKMTzBbwi9YA1kTrQDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:20:56.700336Z","bundle_sha256":"e65137c7f457173ddbb5c8c0d1e2c8fcb6fab3a84225c78a49482e7b16e39e13"}}