{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7P72UKZVCK6EIGQWNW7XSG4467","short_pith_number":"pith:7P72UKZV","schema_version":"1.0","canonical_sha256":"fbffaa2b3512bc441a166dbf791b9cf7e5f0fca329b5c795258e893ebc42a8a5","source":{"kind":"arxiv","id":"1909.01575","version":1},"attestation_state":"computed","paper":{"title":"Learning sparse representations in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"David C. Noelle, Jacob Rafati","submitted_at":"2019-09-04T06:58:32Z","abstract_excerpt":"Reinforcement learning (RL) algorithms allow artificial agents to improve their selection of actions to increase rewarding experiences in their environments. Temporal Difference (TD) Learning -- a model-free RL method -- is a leading account of the midbrain dopamine system and the basal ganglia in reinforcement learning. These algorithms typically learn a mapping from the agent's current sensed state to a selected action (known as a policy function) via learning a value function (expected future rewards). TD Learning methods have been very successful on a broad range of control tasks, but lear"},"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":"1909.01575","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-04T06:58:32Z","cross_cats_sorted":["cs.AI","cs.NE","cs.RO","stat.ML"],"title_canon_sha256":"199b45f7e35f12df860e2bef7f6e7eb8bff629d94b482a02769c69d4abe1a855","abstract_canon_sha256":"96a0c1aaac16d3ed2c451bf966590a42445d26f5c0cef724569e263708861eb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:17.620187Z","signature_b64":"eS0tNPaUGEgEKsq34g4/7Y3gNtCXx7qD2/QmW5wktFJ/lA9BY17qzFUkultn/ZmWZ/7HbLlYz6q5+6v6RyJ4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbffaa2b3512bc441a166dbf791b9cf7e5f0fca329b5c795258e893ebc42a8a5","last_reissued_at":"2026-07-05T00:02:17.619724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:17.619724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning sparse representations in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"David C. Noelle, Jacob Rafati","submitted_at":"2019-09-04T06:58:32Z","abstract_excerpt":"Reinforcement learning (RL) algorithms allow artificial agents to improve their selection of actions to increase rewarding experiences in their environments. Temporal Difference (TD) Learning -- a model-free RL method -- is a leading account of the midbrain dopamine system and the basal ganglia in reinforcement learning. These algorithms typically learn a mapping from the agent's current sensed state to a selected action (known as a policy function) via learning a value function (expected future rewards). TD Learning methods have been very successful on a broad range of control tasks, but lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01575","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/1909.01575/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":"1909.01575","created_at":"2026-07-05T00:02:17.619780+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.01575v1","created_at":"2026-07-05T00:02:17.619780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01575","created_at":"2026-07-05T00:02:17.619780+00:00"},{"alias_kind":"pith_short_12","alias_value":"7P72UKZVCK6E","created_at":"2026-07-05T00:02:17.619780+00:00"},{"alias_kind":"pith_short_16","alias_value":"7P72UKZVCK6EIGQW","created_at":"2026-07-05T00:02:17.619780+00:00"},{"alias_kind":"pith_short_8","alias_value":"7P72UKZV","created_at":"2026-07-05T00:02:17.619780+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.08893","citing_title":"Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse Codes","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467","json":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467.json","graph_json":"https://pith.science/api/pith-number/7P72UKZVCK6EIGQWNW7XSG4467/graph.json","events_json":"https://pith.science/api/pith-number/7P72UKZVCK6EIGQWNW7XSG4467/events.json","paper":"https://pith.science/paper/7P72UKZV"},"agent_actions":{"view_html":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467","download_json":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467.json","view_paper":"https://pith.science/paper/7P72UKZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.01575&json=true","fetch_graph":"https://pith.science/api/pith-number/7P72UKZVCK6EIGQWNW7XSG4467/graph.json","fetch_events":"https://pith.science/api/pith-number/7P72UKZVCK6EIGQWNW7XSG4467/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467/action/storage_attestation","attest_author":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467/action/author_attestation","sign_citation":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467/action/citation_signature","submit_replication":"https://pith.science/pith/7P72UKZVCK6EIGQWNW7XSG4467/action/replication_record"}},"created_at":"2026-07-05T00:02:17.619780+00:00","updated_at":"2026-07-05T00:02:17.619780+00:00"}