{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DXJQ62ONZDFS25GOL6GMVTX7DN","short_pith_number":"pith:DXJQ62ON","schema_version":"1.0","canonical_sha256":"1dd30f69cdc8cb2d74ce5f8ccaceff1b40791f02f4cd499e29e6cb426791e559","source":{"kind":"arxiv","id":"1811.02073","version":2},"attestation_state":"computed","paper":{"title":"QUOTA: The Quantile Option Architecture for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Borislav Mavrin, Hengshuai Yao, Linglong Kong, Shangtong Zhang","submitted_at":"2018-11-05T22:49:03Z","abstract_excerpt":"In this paper, we propose the Quantile Option Architecture (QUOTA) for exploration based on recent advances in distributional reinforcement learning (RL). In QUOTA, decision making is based on quantiles of a value distribution, not only the mean. QUOTA provides a new dimension for exploration via making use of both optimism and pessimism of a value distribution. We demonstrate the performance advantage of QUOTA in both challenging video games and physical robot simulators."},"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":"1811.02073","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T22:49:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"87d1aa9049ef9a3ed03484fb7f84eb3d2b61db78ffb490e90999ce73349d9e33","abstract_canon_sha256":"6eac096b55be2a13eb55f82e96f9193ddba55a81f8628b354e0aef115ba8959b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:19.139067Z","signature_b64":"OF0lrgi8NFJLIPBuT9vhtXYcBfhmUTNe1iulA8MMUyj/0uN1SLC1VCe6YSmG3yHWLxE+EcUczK+/6t6JoheiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dd30f69cdc8cb2d74ce5f8ccaceff1b40791f02f4cd499e29e6cb426791e559","last_reissued_at":"2026-05-18T00:01:19.138591Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:19.138591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QUOTA: The Quantile Option Architecture for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Borislav Mavrin, Hengshuai Yao, Linglong Kong, Shangtong Zhang","submitted_at":"2018-11-05T22:49:03Z","abstract_excerpt":"In this paper, we propose the Quantile Option Architecture (QUOTA) for exploration based on recent advances in distributional reinforcement learning (RL). In QUOTA, decision making is based on quantiles of a value distribution, not only the mean. QUOTA provides a new dimension for exploration via making use of both optimism and pessimism of a value distribution. We demonstrate the performance advantage of QUOTA in both challenging video games and physical robot simulators."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02073","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1811.02073","created_at":"2026-05-18T00:01:19.138655+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.02073v2","created_at":"2026-05-18T00:01:19.138655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02073","created_at":"2026-05-18T00:01:19.138655+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXJQ62ONZDFS","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXJQ62ONZDFS25GO","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXJQ62ON","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04269","citing_title":"A Scheme for Dynamic Risk-Sensitive Sequential Decision Making","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXJQ62ONZDFS25GOL6GMVTX7DN","json":"https://pith.science/pith/DXJQ62ONZDFS25GOL6GMVTX7DN.json","graph_json":"https://pith.science/api/pith-number/DXJQ62ONZDFS25GOL6GMVTX7DN/graph.json","events_json":"https://pith.science/api/pith-number/DXJQ62ONZDFS25GOL6GMVTX7DN/events.json","paper":"https://pith.science/paper/DXJQ62ON"},"agent_actions":{"view_html":"https://pith.science/pith/DXJQ62ONZDFS25GOL6GMVTX7DN","download_json":"https://pith.science/pith/DXJQ62ONZDFS25GOL6GMVTX7DN.json","view_paper":"https://pith.science/paper/DXJQ62ON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.02073&json=true","fetch_graph":"https://pith.science/api/pith-number/DXJQ62ONZDFS25GOL6GMVTX7DN/graph.json","fetch_events":"https://pith.science/api/pith-number/DXJQ62ONZDFS25GOL6GMVTX7DN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXJQ62ONZDFS25GOL6GMVTX7DN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXJQ62ONZDFS25GOL6GMVTX7DN/action/storage_attestation","attest_author":"https://pith.science/pith/DXJQ62ONZDFS25GOL6GMVTX7DN/action/author_attestation","sign_citation":"https://pith.science/pith/DXJQ62ONZDFS25GOL6GMVTX7DN/action/citation_signature","submit_replication":"https://pith.science/pith/DXJQ62ONZDFS25GOL6GMVTX7DN/action/replication_record"}},"created_at":"2026-05-18T00:01:19.138655+00:00","updated_at":"2026-05-18T00:01:19.138655+00:00"}