{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:E5ZHU2ZBCW5AGC4Y6J6YLZJPKN","short_pith_number":"pith:E5ZHU2ZB","canonical_record":{"source":{"id":"1803.00297","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-01T10:53:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a85b952fe99cfaaaf0857b0fb65f871d051306c70d501703cd990fc30379e253","abstract_canon_sha256":"37439a5dc621bc2666cc4b209f2e12f05bb189fc3a8ac84c654200e178b64a8f"},"schema_version":"1.0"},"canonical_sha256":"27727a6b2115ba030b98f27d85e52f53686bd4eb467c171ab41d957967ab7d47","source":{"kind":"arxiv","id":"1803.00297","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.00297","created_at":"2026-05-18T00:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"1803.00297v1","created_at":"2026-05-18T00:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00297","created_at":"2026-05-18T00:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"E5ZHU2ZBCW5A","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"E5ZHU2ZBCW5AGC4Y","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"E5ZHU2ZB","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:E5ZHU2ZBCW5AGC4Y6J6YLZJPKN","target":"record","payload":{"canonical_record":{"source":{"id":"1803.00297","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-01T10:53:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a85b952fe99cfaaaf0857b0fb65f871d051306c70d501703cd990fc30379e253","abstract_canon_sha256":"37439a5dc621bc2666cc4b209f2e12f05bb189fc3a8ac84c654200e178b64a8f"},"schema_version":"1.0"},"canonical_sha256":"27727a6b2115ba030b98f27d85e52f53686bd4eb467c171ab41d957967ab7d47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:12.702279Z","signature_b64":"jdEXD7/GeUA6KMNwyMf30y+p23ZZqQcIosn11jtUQdL1db539li/D9XS3kO01mCqQsV3lFZDg/bklHq6WSZoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27727a6b2115ba030b98f27d85e52f53686bd4eb467c171ab41d957967ab7d47","last_reissued_at":"2026-05-18T00:22:12.701732Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:12.701732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.00297","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LWhoq1Z8Hre2zuR4YJHvyipZAoWKlhFbRQdvDgdebMefOXDAdjaVbvAidSFDTbfMS4vtjKnaiaF7TpxFpTAlBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:57:12.557511Z"},"content_sha256":"46801103322ef2cf5b30f65c45031c64c87a8c61d9fefce68151277c75f56ee7","schema_version":"1.0","event_id":"sha256:46801103322ef2cf5b30f65c45031c64c87a8c61d9fefce68151277c75f56ee7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:E5ZHU2ZBCW5AGC4Y6J6YLZJPKN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Q-CP: Learning Action Values for Cooperative Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Daniele Nardi, Francesco Riccio, Roberto Capobianco","submitted_at":"2018-03-01T10:53:04Z","abstract_excerpt":"Research on multi-robot systems has demonstrated promising results in manifold applications and domains. Still, efficiently learning an effective robot behaviors is very difficult, due to unstructured scenarios, high uncertainties, and large state dimensionality (e.g. hyper-redundant and groups of robot). To alleviate this problem, we present Q-CP a cooperative model-based reinforcement learning algorithm, which exploits action values to both (1) guide the exploration of the state space and (2) generate effective policies. Specifically, we exploit Q-learning to attack the curse-of-dimensionali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00297","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8H1H7dVXjYi+6isxoKClAHDF3WaDqdbFhC1PxaTZq9zTP5mlflNB3/6gl1/6cQ+XJbjlWZYnPhXNghShAFQ+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:57:12.558151Z"},"content_sha256":"f140d8e2da85d220b0e21ac24769a51d36cac666b0c3b32d395eb7955daa3481","schema_version":"1.0","event_id":"sha256:f140d8e2da85d220b0e21ac24769a51d36cac666b0c3b32d395eb7955daa3481"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E5ZHU2ZBCW5AGC4Y6J6YLZJPKN/bundle.json","state_url":"https://pith.science/pith/E5ZHU2ZBCW5AGC4Y6J6YLZJPKN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E5ZHU2ZBCW5AGC4Y6J6YLZJPKN/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":"2026-06-08T02:57:12Z","links":{"resolver":"https://pith.science/pith/E5ZHU2ZBCW5AGC4Y6J6YLZJPKN","bundle":"https://pith.science/pith/E5ZHU2ZBCW5AGC4Y6J6YLZJPKN/bundle.json","state":"https://pith.science/pith/E5ZHU2ZBCW5AGC4Y6J6YLZJPKN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E5ZHU2ZBCW5AGC4Y6J6YLZJPKN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:E5ZHU2ZBCW5AGC4Y6J6YLZJPKN","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":"37439a5dc621bc2666cc4b209f2e12f05bb189fc3a8ac84c654200e178b64a8f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-01T10:53:04Z","title_canon_sha256":"a85b952fe99cfaaaf0857b0fb65f871d051306c70d501703cd990fc30379e253"},"schema_version":"1.0","source":{"id":"1803.00297","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.00297","created_at":"2026-05-18T00:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"1803.00297v1","created_at":"2026-05-18T00:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00297","created_at":"2026-05-18T00:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"E5ZHU2ZBCW5A","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"E5ZHU2ZBCW5AGC4Y","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"E5ZHU2ZB","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:f140d8e2da85d220b0e21ac24769a51d36cac666b0c3b32d395eb7955daa3481","target":"graph","created_at":"2026-05-18T00:22:12Z","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":"Research on multi-robot systems has demonstrated promising results in manifold applications and domains. Still, efficiently learning an effective robot behaviors is very difficult, due to unstructured scenarios, high uncertainties, and large state dimensionality (e.g. hyper-redundant and groups of robot). To alleviate this problem, we present Q-CP a cooperative model-based reinforcement learning algorithm, which exploits action values to both (1) guide the exploration of the state space and (2) generate effective policies. Specifically, we exploit Q-learning to attack the curse-of-dimensionali","authors_text":"Daniele Nardi, Francesco Riccio, Roberto Capobianco","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-01T10:53:04Z","title":"Q-CP: Learning Action Values for Cooperative Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00297","kind":"arxiv","version":1},"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":"sha256:46801103322ef2cf5b30f65c45031c64c87a8c61d9fefce68151277c75f56ee7","target":"record","created_at":"2026-05-18T00:22:12Z","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":"37439a5dc621bc2666cc4b209f2e12f05bb189fc3a8ac84c654200e178b64a8f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-01T10:53:04Z","title_canon_sha256":"a85b952fe99cfaaaf0857b0fb65f871d051306c70d501703cd990fc30379e253"},"schema_version":"1.0","source":{"id":"1803.00297","kind":"arxiv","version":1}},"canonical_sha256":"27727a6b2115ba030b98f27d85e52f53686bd4eb467c171ab41d957967ab7d47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27727a6b2115ba030b98f27d85e52f53686bd4eb467c171ab41d957967ab7d47","first_computed_at":"2026-05-18T00:22:12.701732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:12.701732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jdEXD7/GeUA6KMNwyMf30y+p23ZZqQcIosn11jtUQdL1db539li/D9XS3kO01mCqQsV3lFZDg/bklHq6WSZoAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:12.702279Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.00297","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46801103322ef2cf5b30f65c45031c64c87a8c61d9fefce68151277c75f56ee7","sha256:f140d8e2da85d220b0e21ac24769a51d36cac666b0c3b32d395eb7955daa3481"],"state_sha256":"2a552a1a5167e79a12ba3956634103475ba0eff6fd9fc9f5d27f1c3246919d8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y0pCfUMmDDrumAhQ/9YlaQYeLlZ14E3gI/AVIXOcN8Od4qF+XY05gKKpzls8zjdl5Dmz/M+A0axHegrJU6bFAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T02:57:12.562145Z","bundle_sha256":"b76fcc3de833c5a978bae71033a0d4eb19ffcaef495c918c8fcc53e284dce103"}}