{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:OHY5FSIRFYWOD4Y6PGQXBTSJID","short_pith_number":"pith:OHY5FSIR","canonical_record":{"source":{"id":"1108.4698","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2011-08-23T20:28:01Z","cross_cats_sorted":["cs.SY","math.OC"],"title_canon_sha256":"3f27827f906b96cdb09a6c77f239848e656a48563befa019b92a9e0348f02c43","abstract_canon_sha256":"87421ca9f30b0b8e6ca3dc33123b18a58615da6c66c9c24498646b462d6e0c57"},"schema_version":"1.0"},"canonical_sha256":"71f1d2c9112e2ce1f31e79a170ce4940c4ef26ce9dad919246b2907dca8abe8b","source":{"kind":"arxiv","id":"1108.4698","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1108.4698","created_at":"2026-05-18T04:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"1108.4698v2","created_at":"2026-05-18T04:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1108.4698","created_at":"2026-05-18T04:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"OHY5FSIRFYWO","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_16","alias_value":"OHY5FSIRFYWOD4Y6","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_8","alias_value":"OHY5FSIR","created_at":"2026-05-18T12:26:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:OHY5FSIRFYWOD4Y6PGQXBTSJID","target":"record","payload":{"canonical_record":{"source":{"id":"1108.4698","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2011-08-23T20:28:01Z","cross_cats_sorted":["cs.SY","math.OC"],"title_canon_sha256":"3f27827f906b96cdb09a6c77f239848e656a48563befa019b92a9e0348f02c43","abstract_canon_sha256":"87421ca9f30b0b8e6ca3dc33123b18a58615da6c66c9c24498646b462d6e0c57"},"schema_version":"1.0"},"canonical_sha256":"71f1d2c9112e2ce1f31e79a170ce4940c4ef26ce9dad919246b2907dca8abe8b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:14:28.712640Z","signature_b64":"KxAQz1YKKPqWCYLTqumgjJ2x5lMrDSf8PBTAlPCUKS9uEzCFyPrCOyX3i4Tq4puvXF3XDuhJ7GidBZJ8YORBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71f1d2c9112e2ce1f31e79a170ce4940c4ef26ce9dad919246b2907dca8abe8b","last_reissued_at":"2026-05-18T04:14:28.711936Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:14:28.711936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1108.4698","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":"2026-05-18T04:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JVmkdJ9o4zehaOhcTAF7FHngs4IupCJp0hxcA9O3uMIUHWw3x3GMm5UwWv56gHUqgd9k8pQo0MVsZxEw1b9qCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:08:06.075151Z"},"content_sha256":"8daaadf39b3d7bc0af41f99c47133c4763544aa29f6033914617acb6538f7256","schema_version":"1.0","event_id":"sha256:8daaadf39b3d7bc0af41f99c47133c4763544aa29f6033914617acb6538f7256"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:OHY5FSIRFYWOD4Y6PGQXBTSJID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Least Squares Temporal Difference Actor-Critic Methods with Applications to Robot Motion Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","math.OC"],"primary_cat":"cs.RO","authors_text":"Calin A. Belta, Ioannis Ch. Paschalidis, Jing Wang, Morteza Lahijanian, Reza Moazzez Estanjini, Xu Chu Ding","submitted_at":"2011-08-23T20:28:01Z","abstract_excerpt":"We consider the problem of finding a control policy for a Markov Decision Process (MDP) to maximize the probability of reaching some states while avoiding some other states. This problem is motivated by applications in robotics, where such problems naturally arise when probabilistic models of robot motion are required to satisfy temporal logic task specifications. We transform this problem into a Stochastic Shortest Path (SSP) problem and develop a new approximate dynamic programming algorithm to solve it. This algorithm is of the actor-critic type and uses a least-square temporal difference l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1108.4698","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":"2026-05-18T04:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7E2jKYYHOLTn42xjn9N6A2HYLrHzSfL+wRR7WhkZjL8ESksLGL3wLzzf9x/IH9EdUM3Sj2sPjnTonxh/UEcqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:08:06.075755Z"},"content_sha256":"b1f59728cff5556982f43469f75942f0ee7c4083be7593cb4342b1242cd12005","schema_version":"1.0","event_id":"sha256:b1f59728cff5556982f43469f75942f0ee7c4083be7593cb4342b1242cd12005"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OHY5FSIRFYWOD4Y6PGQXBTSJID/bundle.json","state_url":"https://pith.science/pith/OHY5FSIRFYWOD4Y6PGQXBTSJID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OHY5FSIRFYWOD4Y6PGQXBTSJID/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":"2026-05-28T23:08:06Z","links":{"resolver":"https://pith.science/pith/OHY5FSIRFYWOD4Y6PGQXBTSJID","bundle":"https://pith.science/pith/OHY5FSIRFYWOD4Y6PGQXBTSJID/bundle.json","state":"https://pith.science/pith/OHY5FSIRFYWOD4Y6PGQXBTSJID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OHY5FSIRFYWOD4Y6PGQXBTSJID/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:OHY5FSIRFYWOD4Y6PGQXBTSJID","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":"87421ca9f30b0b8e6ca3dc33123b18a58615da6c66c9c24498646b462d6e0c57","cross_cats_sorted":["cs.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2011-08-23T20:28:01Z","title_canon_sha256":"3f27827f906b96cdb09a6c77f239848e656a48563befa019b92a9e0348f02c43"},"schema_version":"1.0","source":{"id":"1108.4698","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1108.4698","created_at":"2026-05-18T04:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"1108.4698v2","created_at":"2026-05-18T04:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1108.4698","created_at":"2026-05-18T04:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"OHY5FSIRFYWO","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_16","alias_value":"OHY5FSIRFYWOD4Y6","created_at":"2026-05-18T12:26:37Z"},{"alias_kind":"pith_short_8","alias_value":"OHY5FSIR","created_at":"2026-05-18T12:26:37Z"}],"graph_snapshots":[{"event_id":"sha256:b1f59728cff5556982f43469f75942f0ee7c4083be7593cb4342b1242cd12005","target":"graph","created_at":"2026-05-18T04:14:28Z","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":"We consider the problem of finding a control policy for a Markov Decision Process (MDP) to maximize the probability of reaching some states while avoiding some other states. This problem is motivated by applications in robotics, where such problems naturally arise when probabilistic models of robot motion are required to satisfy temporal logic task specifications. We transform this problem into a Stochastic Shortest Path (SSP) problem and develop a new approximate dynamic programming algorithm to solve it. This algorithm is of the actor-critic type and uses a least-square temporal difference l","authors_text":"Calin A. Belta, Ioannis Ch. Paschalidis, Jing Wang, Morteza Lahijanian, Reza Moazzez Estanjini, Xu Chu Ding","cross_cats":["cs.SY","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2011-08-23T20:28:01Z","title":"Least Squares Temporal Difference Actor-Critic Methods with Applications to Robot Motion Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1108.4698","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":"sha256:8daaadf39b3d7bc0af41f99c47133c4763544aa29f6033914617acb6538f7256","target":"record","created_at":"2026-05-18T04:14:28Z","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":"87421ca9f30b0b8e6ca3dc33123b18a58615da6c66c9c24498646b462d6e0c57","cross_cats_sorted":["cs.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2011-08-23T20:28:01Z","title_canon_sha256":"3f27827f906b96cdb09a6c77f239848e656a48563befa019b92a9e0348f02c43"},"schema_version":"1.0","source":{"id":"1108.4698","kind":"arxiv","version":2}},"canonical_sha256":"71f1d2c9112e2ce1f31e79a170ce4940c4ef26ce9dad919246b2907dca8abe8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71f1d2c9112e2ce1f31e79a170ce4940c4ef26ce9dad919246b2907dca8abe8b","first_computed_at":"2026-05-18T04:14:28.711936Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:14:28.711936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KxAQz1YKKPqWCYLTqumgjJ2x5lMrDSf8PBTAlPCUKS9uEzCFyPrCOyX3i4Tq4puvXF3XDuhJ7GidBZJ8YORBDg==","signature_status":"signed_v1","signed_at":"2026-05-18T04:14:28.712640Z","signed_message":"canonical_sha256_bytes"},"source_id":"1108.4698","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8daaadf39b3d7bc0af41f99c47133c4763544aa29f6033914617acb6538f7256","sha256:b1f59728cff5556982f43469f75942f0ee7c4083be7593cb4342b1242cd12005"],"state_sha256":"1317f47aeeb001e8610dc3b5b9fdfdbd968cfc751003bc140d7dc59137f70e15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VyeMVbWWSrRJGFb4HNj0LvWMXVOUlUdeW4YsGWCiuZ5Uj9YMQoJ7vY7RI2ItX4ySai1t/SvJejzRKWshnaJ8Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T23:08:06.078751Z","bundle_sha256":"9fc2183094f5a284bc11460b3612b5550197b20661700b2d12cb8324ebf91737"}}