{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:BHI3LFVJKQXTXFWZ4RRRWHL5ZI","short_pith_number":"pith:BHI3LFVJ","schema_version":"1.0","canonical_sha256":"09d1b596a9542f3b96d9e4631b1d7dca21f6c386a742d5b987bfc486208465be","source":{"kind":"arxiv","id":"1105.1749","version":2},"attestation_state":"computed","paper":{"title":"A Real-Time Model-Based Reinforcement Learning Architecture for Robot Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SE"],"primary_cat":"cs.AI","authors_text":"Michael Quinlan, Peter Stone, Todd Hester","submitted_at":"2011-05-09T18:17:20Z","abstract_excerpt":"Reinforcement Learning (RL) is a method for learning decision-making tasks that could enable robots to learn and adapt to their situation on-line. For an RL algorithm to be practical for robotic control tasks, it must learn in very few actions, while continually taking those actions in real-time. Existing model-based RL methods learn in relatively few actions, but typically take too much time between each action for practical on-line learning. In this paper, we present a novel parallel architecture for model-based RL that runs in real-time by 1) taking advantage of sample-based approximate pla"},"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":"1105.1749","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-05-09T18:17:20Z","cross_cats_sorted":["cs.RO","cs.SE"],"title_canon_sha256":"781d4645c7e00715b67d8f54cd042e32f36b0c19f9dfa413814cdf3a96e338f8","abstract_canon_sha256":"aa20650f4f2ab35d720e7bcba89520379972c18c16076cc1b4b9fdf74ff6f4aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:22:00.484810Z","signature_b64":"b7XVMcD6PAKPlSsPXk7SOpizqTcDfDTGRX7VQ8Ohosuy912isgkicD+744K99ax0X9QxbhiVii7w1s3SWk/9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09d1b596a9542f3b96d9e4631b1d7dca21f6c386a742d5b987bfc486208465be","last_reissued_at":"2026-05-18T02:22:00.484100Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:22:00.484100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Real-Time Model-Based Reinforcement Learning Architecture for Robot Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SE"],"primary_cat":"cs.AI","authors_text":"Michael Quinlan, Peter Stone, Todd Hester","submitted_at":"2011-05-09T18:17:20Z","abstract_excerpt":"Reinforcement Learning (RL) is a method for learning decision-making tasks that could enable robots to learn and adapt to their situation on-line. For an RL algorithm to be practical for robotic control tasks, it must learn in very few actions, while continually taking those actions in real-time. Existing model-based RL methods learn in relatively few actions, but typically take too much time between each action for practical on-line learning. In this paper, we present a novel parallel architecture for model-based RL that runs in real-time by 1) taking advantage of sample-based approximate pla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1105.1749","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":"1105.1749","created_at":"2026-05-18T02:22:00.484215+00:00"},{"alias_kind":"arxiv_version","alias_value":"1105.1749v2","created_at":"2026-05-18T02:22:00.484215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1105.1749","created_at":"2026-05-18T02:22:00.484215+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHI3LFVJKQXT","created_at":"2026-05-18T12:26:24.575870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHI3LFVJKQXTXFWZ","created_at":"2026-05-18T12:26:24.575870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHI3LFVJ","created_at":"2026-05-18T12:26:24.575870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2004.07219","citing_title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI","json":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI.json","graph_json":"https://pith.science/api/pith-number/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/graph.json","events_json":"https://pith.science/api/pith-number/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/events.json","paper":"https://pith.science/paper/BHI3LFVJ"},"agent_actions":{"view_html":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI","download_json":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI.json","view_paper":"https://pith.science/paper/BHI3LFVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1105.1749&json=true","fetch_graph":"https://pith.science/api/pith-number/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/graph.json","fetch_events":"https://pith.science/api/pith-number/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/action/storage_attestation","attest_author":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/action/author_attestation","sign_citation":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/action/citation_signature","submit_replication":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/action/replication_record"}},"created_at":"2026-05-18T02:22:00.484215+00:00","updated_at":"2026-05-18T02:22:00.484215+00:00"}