{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PKMJRPLGD4TPXCTLQEAQG42MPX","short_pith_number":"pith:PKMJRPLG","schema_version":"1.0","canonical_sha256":"7a9898bd661f26fb8a6b810103734c7debff8566e851620afc16bf4a1fd00187","source":{"kind":"arxiv","id":"1811.06626","version":1},"attestation_state":"computed","paper":{"title":"The Utility of Sparse Representations for Control in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lei Le, Martha White, Raksha Kumaraswamy, Vincent Liu","submitted_at":"2018-11-15T23:23:36Z","abstract_excerpt":"We investigate sparse representations for control in reinforcement learning. While these representations are widely used in computer vision, their prevalence in reinforcement learning is limited to sparse coding where extracting representations for new data can be computationally intensive. Here, we begin by demonstrating that learning a control policy incrementally with a representation from a standard neural network fails in classic control domains, whereas learning with a representation obtained from a neural network that has sparsity properties enforced is effective. We provide evidence th"},"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":"1811.06626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T23:23:36Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"260cbf450edb13b2f48d61f83e5980ca58399d77d3173a58ce1bbb4db2249217","abstract_canon_sha256":"351f254b105934f962935b1105ee0550a032d385083763c93a27f0136fc41906"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:34.316451Z","signature_b64":"FeNn6o19J4Z5kGHnT50566a+McK3JiXw5HM0MsqgIFAgl3aW1DPa/B7QPBRudUg5y8F9Lw70mPORxwWMuVIACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a9898bd661f26fb8a6b810103734c7debff8566e851620afc16bf4a1fd00187","last_reissued_at":"2026-05-18T00:00:34.315809Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:34.315809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Utility of Sparse Representations for Control in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lei Le, Martha White, Raksha Kumaraswamy, Vincent Liu","submitted_at":"2018-11-15T23:23:36Z","abstract_excerpt":"We investigate sparse representations for control in reinforcement learning. While these representations are widely used in computer vision, their prevalence in reinforcement learning is limited to sparse coding where extracting representations for new data can be computationally intensive. Here, we begin by demonstrating that learning a control policy incrementally with a representation from a standard neural network fails in classic control domains, whereas learning with a representation obtained from a neural network that has sparsity properties enforced is effective. We provide evidence th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.06626","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":""},"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":"1811.06626","created_at":"2026-05-18T00:00:34.315913+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.06626v1","created_at":"2026-05-18T00:00:34.315913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.06626","created_at":"2026-05-18T00:00:34.315913+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKMJRPLGD4TP","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKMJRPLGD4TPXCTL","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKMJRPLG","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08893","citing_title":"Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse Codes","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKMJRPLGD4TPXCTLQEAQG42MPX","json":"https://pith.science/pith/PKMJRPLGD4TPXCTLQEAQG42MPX.json","graph_json":"https://pith.science/api/pith-number/PKMJRPLGD4TPXCTLQEAQG42MPX/graph.json","events_json":"https://pith.science/api/pith-number/PKMJRPLGD4TPXCTLQEAQG42MPX/events.json","paper":"https://pith.science/paper/PKMJRPLG"},"agent_actions":{"view_html":"https://pith.science/pith/PKMJRPLGD4TPXCTLQEAQG42MPX","download_json":"https://pith.science/pith/PKMJRPLGD4TPXCTLQEAQG42MPX.json","view_paper":"https://pith.science/paper/PKMJRPLG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.06626&json=true","fetch_graph":"https://pith.science/api/pith-number/PKMJRPLGD4TPXCTLQEAQG42MPX/graph.json","fetch_events":"https://pith.science/api/pith-number/PKMJRPLGD4TPXCTLQEAQG42MPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKMJRPLGD4TPXCTLQEAQG42MPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKMJRPLGD4TPXCTLQEAQG42MPX/action/storage_attestation","attest_author":"https://pith.science/pith/PKMJRPLGD4TPXCTLQEAQG42MPX/action/author_attestation","sign_citation":"https://pith.science/pith/PKMJRPLGD4TPXCTLQEAQG42MPX/action/citation_signature","submit_replication":"https://pith.science/pith/PKMJRPLGD4TPXCTLQEAQG42MPX/action/replication_record"}},"created_at":"2026-05-18T00:00:34.315913+00:00","updated_at":"2026-05-18T00:00:34.315913+00:00"}