{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:BHI3LFVJKQXTXFWZ4RRRWHL5ZI","short_pith_number":"pith:BHI3LFVJ","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"},"canonical_sha256":"09d1b596a9542f3b96d9e4631b1d7dca21f6c386a742d5b987bfc486208465be","source":{"kind":"arxiv","id":"1105.1749","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1105.1749","created_at":"2026-05-18T02:22:00Z"},{"alias_kind":"arxiv_version","alias_value":"1105.1749v2","created_at":"2026-05-18T02:22:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1105.1749","created_at":"2026-05-18T02:22:00Z"},{"alias_kind":"pith_short_12","alias_value":"BHI3LFVJKQXT","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"BHI3LFVJKQXTXFWZ","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"BHI3LFVJ","created_at":"2026-05-18T12:26:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:BHI3LFVJKQXTXFWZ4RRRWHL5ZI","target":"record","payload":{"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"},"canonical_sha256":"09d1b596a9542f3b96d9e4631b1d7dca21f6c386a742d5b987bfc486208465be","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"},"source_kind":"arxiv","source_id":"1105.1749","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:22:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BwO0/tOSy/Ek59S5Mt9iAgiB+WuVmKG10FNH5MyHXhbCMjECrfFid2+62ZV8GdOovr0xjbl/QrQ5UGD5i2BVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:01:47.800892Z"},"content_sha256":"202211f1ee1d3ed9691b9642f9983fbf9ddeb1cb352a21b1ca2e5c746595e693","schema_version":"1.0","event_id":"sha256:202211f1ee1d3ed9691b9642f9983fbf9ddeb1cb352a21b1ca2e5c746595e693"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:BHI3LFVJKQXTXFWZ4RRRWHL5ZI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:22:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PHNn33PVDWwuDPKCNOmk+C24Rxx0jE7aN8x4pgHZl/uODVglptm+VEfqd/6c0020tBWuMWe2dAz8fNSpDdwqDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:01:47.801533Z"},"content_sha256":"010974fce003b40ee48d6be10f1b33a76fda51389b28fa4541665eb7e248e719","schema_version":"1.0","event_id":"sha256:010974fce003b40ee48d6be10f1b33a76fda51389b28fa4541665eb7e248e719"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/bundle.json","state_url":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T14:01:47Z","links":{"resolver":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI","bundle":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/bundle.json","state":"https://pith.science/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BHI3LFVJKQXTXFWZ4RRRWHL5ZI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:BHI3LFVJKQXTXFWZ4RRRWHL5ZI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"aa20650f4f2ab35d720e7bcba89520379972c18c16076cc1b4b9fdf74ff6f4aa","cross_cats_sorted":["cs.RO","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-05-09T18:17:20Z","title_canon_sha256":"781d4645c7e00715b67d8f54cd042e32f36b0c19f9dfa413814cdf3a96e338f8"},"schema_version":"1.0","source":{"id":"1105.1749","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1105.1749","created_at":"2026-05-18T02:22:00Z"},{"alias_kind":"arxiv_version","alias_value":"1105.1749v2","created_at":"2026-05-18T02:22:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1105.1749","created_at":"2026-05-18T02:22:00Z"},{"alias_kind":"pith_short_12","alias_value":"BHI3LFVJKQXT","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"BHI3LFVJKQXTXFWZ","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"BHI3LFVJ","created_at":"2026-05-18T12:26:24Z"}],"graph_snapshots":[{"event_id":"sha256:010974fce003b40ee48d6be10f1b33a76fda51389b28fa4541665eb7e248e719","target":"graph","created_at":"2026-05-18T02:22:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Michael Quinlan, Peter Stone, Todd Hester","cross_cats":["cs.RO","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-05-09T18:17:20Z","title":"A Real-Time Model-Based Reinforcement Learning Architecture for Robot Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1105.1749","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:202211f1ee1d3ed9691b9642f9983fbf9ddeb1cb352a21b1ca2e5c746595e693","target":"record","created_at":"2026-05-18T02:22:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"aa20650f4f2ab35d720e7bcba89520379972c18c16076cc1b4b9fdf74ff6f4aa","cross_cats_sorted":["cs.RO","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-05-09T18:17:20Z","title_canon_sha256":"781d4645c7e00715b67d8f54cd042e32f36b0c19f9dfa413814cdf3a96e338f8"},"schema_version":"1.0","source":{"id":"1105.1749","kind":"arxiv","version":2}},"canonical_sha256":"09d1b596a9542f3b96d9e4631b1d7dca21f6c386a742d5b987bfc486208465be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09d1b596a9542f3b96d9e4631b1d7dca21f6c386a742d5b987bfc486208465be","first_computed_at":"2026-05-18T02:22:00.484100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:22:00.484100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b7XVMcD6PAKPlSsPXk7SOpizqTcDfDTGRX7VQ8Ohosuy912isgkicD+744K99ax0X9QxbhiVii7w1s3SWk/9DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:22:00.484810Z","signed_message":"canonical_sha256_bytes"},"source_id":"1105.1749","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:202211f1ee1d3ed9691b9642f9983fbf9ddeb1cb352a21b1ca2e5c746595e693","sha256:010974fce003b40ee48d6be10f1b33a76fda51389b28fa4541665eb7e248e719"],"state_sha256":"2b265759cc5c9adf24f70e28eb4231b83b0d181414ec51ca98f3c873bdd532ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZF99CbRXI8HC5te3gU3087pPmRqRKMCYPnh/9J6R7JtoOa80Z2fVcIuYyst3tkMua5lBdlN4e0DGdwOP35xEAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T14:01:47.804808Z","bundle_sha256":"85efd56ea9a2bd146c7582e8eb48de5a7fa74b27ee8f24dd5c47524bfc6ebf86"}}