{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2WUKXN6RFZ2GVM7ZBKICIABDFX","short_pith_number":"pith:2WUKXN6R","schema_version":"1.0","canonical_sha256":"d5a8abb7d12e746ab3f90a902400232df29a1f2d34d15206439050ff6669be0c","source":{"kind":"arxiv","id":"1912.06910","version":1},"attestation_state":"computed","paper":{"title":"Adapting Behaviour for Learning Progress","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Ding, David Szepesvari, Diana Borsa, Georg Ostrovski, Simon Osindero, Tom Schaul, Will Dabney","submitted_at":"2019-12-14T19:34:47Z","abstract_excerpt":"Determining what experience to generate to best facilitate learning (i.e. exploration) is one of the distinguishing features and open challenges in reinforcement learning. The advent of distributed agents that interact with parallel instances of the environment has enabled larger scales and greater flexibility, but has not removed the need to tune exploration to the task, because the ideal data for the learning algorithm necessarily depends on its process of learning. We propose to dynamically adapt the data generation by using a non-stationary multi-armed bandit to optimize a proxy of the lea"},"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":"1912.06910","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-14T19:34:47Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4a73955c3c752c24106bff747448d2971711c5ab7d9fa7ac1e8e313bb1d60e71","abstract_canon_sha256":"6a9673d2a8a20c3d2a921d264a5b153e3eb4ee0ce30699dc4d9368805669483e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:26:16.728133Z","signature_b64":"53xVLND2xmxJDbT6RUYGEjDQOzpxAsLDDbSlz8jrITQT369LvgC8P75hCZERu5Rg59HN4r6RUt8NYWWOiSP2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5a8abb7d12e746ab3f90a902400232df29a1f2d34d15206439050ff6669be0c","last_reissued_at":"2026-07-05T00:26:16.727656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:26:16.727656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting Behaviour for Learning Progress","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Ding, David Szepesvari, Diana Borsa, Georg Ostrovski, Simon Osindero, Tom Schaul, Will Dabney","submitted_at":"2019-12-14T19:34:47Z","abstract_excerpt":"Determining what experience to generate to best facilitate learning (i.e. exploration) is one of the distinguishing features and open challenges in reinforcement learning. The advent of distributed agents that interact with parallel instances of the environment has enabled larger scales and greater flexibility, but has not removed the need to tune exploration to the task, because the ideal data for the learning algorithm necessarily depends on its process of learning. We propose to dynamically adapt the data generation by using a non-stationary multi-armed bandit to optimize a proxy of the lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.06910","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/1912.06910/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":"1912.06910","created_at":"2026-07-05T00:26:16.727719+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.06910v1","created_at":"2026-07-05T00:26:16.727719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.06910","created_at":"2026-07-05T00:26:16.727719+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WUKXN6RFZ2G","created_at":"2026-07-05T00:26:16.727719+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WUKXN6RFZ2GVM7Z","created_at":"2026-07-05T00:26:16.727719+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WUKXN6R","created_at":"2026-07-05T00:26:16.727719+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14382","citing_title":"Balans: Multi-Armed Bandits-based Adaptive Large Neighborhood Search for Mixed-Integer Programming Problem","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2WUKXN6RFZ2GVM7ZBKICIABDFX","json":"https://pith.science/pith/2WUKXN6RFZ2GVM7ZBKICIABDFX.json","graph_json":"https://pith.science/api/pith-number/2WUKXN6RFZ2GVM7ZBKICIABDFX/graph.json","events_json":"https://pith.science/api/pith-number/2WUKXN6RFZ2GVM7ZBKICIABDFX/events.json","paper":"https://pith.science/paper/2WUKXN6R"},"agent_actions":{"view_html":"https://pith.science/pith/2WUKXN6RFZ2GVM7ZBKICIABDFX","download_json":"https://pith.science/pith/2WUKXN6RFZ2GVM7ZBKICIABDFX.json","view_paper":"https://pith.science/paper/2WUKXN6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.06910&json=true","fetch_graph":"https://pith.science/api/pith-number/2WUKXN6RFZ2GVM7ZBKICIABDFX/graph.json","fetch_events":"https://pith.science/api/pith-number/2WUKXN6RFZ2GVM7ZBKICIABDFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WUKXN6RFZ2GVM7ZBKICIABDFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WUKXN6RFZ2GVM7ZBKICIABDFX/action/storage_attestation","attest_author":"https://pith.science/pith/2WUKXN6RFZ2GVM7ZBKICIABDFX/action/author_attestation","sign_citation":"https://pith.science/pith/2WUKXN6RFZ2GVM7ZBKICIABDFX/action/citation_signature","submit_replication":"https://pith.science/pith/2WUKXN6RFZ2GVM7ZBKICIABDFX/action/replication_record"}},"created_at":"2026-07-05T00:26:16.727719+00:00","updated_at":"2026-07-05T00:26:16.727719+00:00"}