{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KNV2I6SCYYZXOC7QPSSFILBXXI","short_pith_number":"pith:KNV2I6SC","canonical_record":{"source":{"id":"1910.05512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-12T07:14:33Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"578158dc4105d0b29b078d5e3aad2ad7697b5d59dff3f0364c906fa95c1476ad","abstract_canon_sha256":"b6d35eef77b75dadf73d3cb0018a34f284a170bbe4f4d6cef6e417cc95363d2a"},"schema_version":"1.0"},"canonical_sha256":"536ba47a42c633770bf07ca4542c37ba11be9ebda8f16132ebee3ee31c551459","source":{"kind":"arxiv","id":"1910.05512","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.05512","created_at":"2026-07-05T00:28:24Z"},{"alias_kind":"arxiv_version","alias_value":"1910.05512v1","created_at":"2026-07-05T00:28:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05512","created_at":"2026-07-05T00:28:24Z"},{"alias_kind":"pith_short_12","alias_value":"KNV2I6SCYYZX","created_at":"2026-07-05T00:28:24Z"},{"alias_kind":"pith_short_16","alias_value":"KNV2I6SCYYZXOC7Q","created_at":"2026-07-05T00:28:24Z"},{"alias_kind":"pith_short_8","alias_value":"KNV2I6SC","created_at":"2026-07-05T00:28:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KNV2I6SCYYZXOC7QPSSFILBXXI","target":"record","payload":{"canonical_record":{"source":{"id":"1910.05512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-12T07:14:33Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"578158dc4105d0b29b078d5e3aad2ad7697b5d59dff3f0364c906fa95c1476ad","abstract_canon_sha256":"b6d35eef77b75dadf73d3cb0018a34f284a170bbe4f4d6cef6e417cc95363d2a"},"schema_version":"1.0"},"canonical_sha256":"536ba47a42c633770bf07ca4542c37ba11be9ebda8f16132ebee3ee31c551459","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:24.937390Z","signature_b64":"XuhPz2HLTOjbA6H7c54aATlC3T+xlbIcQFSxCh+f6FIMqiSfndCsXikpAgXcXeptCqzoeU9HsVXMtfJGgo4aAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"536ba47a42c633770bf07ca4542c37ba11be9ebda8f16132ebee3ee31c551459","last_reissued_at":"2026-07-05T00:28:24.936905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:24.936905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.05512","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":"2026-07-05T00:28:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vKIYJIZKTM4d0QEqfFDXGBG8ZRJ7KacA4qA0MDITc36Bx/gCtNAvR2b5QJMFHFnasP7F+uJu8cD6qvhqtJk7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:09:30.777956Z"},"content_sha256":"e40d19aef6806304bed720d59b287ad19f423279faf70df1323303923e7c908f","schema_version":"1.0","event_id":"sha256:e40d19aef6806304bed720d59b287ad19f423279faf70df1323303923e7c908f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KNV2I6SCYYZXOC7QPSSFILBXXI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Influence-Based Multi-Agent Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chongjie Zhang, Jianhao Wang, Tonghan Wang, Yi Wu","submitted_at":"2019-10-12T07:14:33Z","abstract_excerpt":"Intrinsically motivated reinforcement learning aims to address the exploration challenge for sparse-reward tasks. However, the study of exploration methods in transition-dependent multi-agent settings is largely absent from the literature. We aim to take a step towards solving this problem. We present two exploration methods: exploration via information-theoretic influence (EITI) and exploration via decision-theoretic influence (EDTI), by exploiting the role of interaction in coordinated behaviors of agents. EITI uses mutual information to capture influence transition dynamics. EDTI uses a nov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05512","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.05512/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:28:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5fMKaMUdSgl0gmcBKXmE/WzZs5PYDHCPxbiUKYFST1vs+HeC5IJ/JV8MHfLdMcGazOwtYvwkM7hpNVgez8SSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:09:30.778333Z"},"content_sha256":"1e03d7fd2c48e1dbd74dadb33f40477af71db67478308823fbcee7c49979d903","schema_version":"1.0","event_id":"sha256:1e03d7fd2c48e1dbd74dadb33f40477af71db67478308823fbcee7c49979d903"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI/bundle.json","state_url":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KNV2I6SCYYZXOC7QPSSFILBXXI/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":"2026-07-06T18:09:30Z","links":{"resolver":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI","bundle":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI/bundle.json","state":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KNV2I6SCYYZXOC7QPSSFILBXXI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KNV2I6SCYYZXOC7QPSSFILBXXI","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":"b6d35eef77b75dadf73d3cb0018a34f284a170bbe4f4d6cef6e417cc95363d2a","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-12T07:14:33Z","title_canon_sha256":"578158dc4105d0b29b078d5e3aad2ad7697b5d59dff3f0364c906fa95c1476ad"},"schema_version":"1.0","source":{"id":"1910.05512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.05512","created_at":"2026-07-05T00:28:24Z"},{"alias_kind":"arxiv_version","alias_value":"1910.05512v1","created_at":"2026-07-05T00:28:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05512","created_at":"2026-07-05T00:28:24Z"},{"alias_kind":"pith_short_12","alias_value":"KNV2I6SCYYZX","created_at":"2026-07-05T00:28:24Z"},{"alias_kind":"pith_short_16","alias_value":"KNV2I6SCYYZXOC7Q","created_at":"2026-07-05T00:28:24Z"},{"alias_kind":"pith_short_8","alias_value":"KNV2I6SC","created_at":"2026-07-05T00:28:24Z"}],"graph_snapshots":[{"event_id":"sha256:1e03d7fd2c48e1dbd74dadb33f40477af71db67478308823fbcee7c49979d903","target":"graph","created_at":"2026-07-05T00:28:24Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1910.05512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Intrinsically motivated reinforcement learning aims to address the exploration challenge for sparse-reward tasks. However, the study of exploration methods in transition-dependent multi-agent settings is largely absent from the literature. We aim to take a step towards solving this problem. We present two exploration methods: exploration via information-theoretic influence (EITI) and exploration via decision-theoretic influence (EDTI), by exploiting the role of interaction in coordinated behaviors of agents. EITI uses mutual information to capture influence transition dynamics. EDTI uses a nov","authors_text":"Chongjie Zhang, Jianhao Wang, Tonghan Wang, Yi Wu","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-12T07:14:33Z","title":"Influence-Based Multi-Agent Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05512","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:e40d19aef6806304bed720d59b287ad19f423279faf70df1323303923e7c908f","target":"record","created_at":"2026-07-05T00:28:24Z","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":"b6d35eef77b75dadf73d3cb0018a34f284a170bbe4f4d6cef6e417cc95363d2a","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-12T07:14:33Z","title_canon_sha256":"578158dc4105d0b29b078d5e3aad2ad7697b5d59dff3f0364c906fa95c1476ad"},"schema_version":"1.0","source":{"id":"1910.05512","kind":"arxiv","version":1}},"canonical_sha256":"536ba47a42c633770bf07ca4542c37ba11be9ebda8f16132ebee3ee31c551459","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"536ba47a42c633770bf07ca4542c37ba11be9ebda8f16132ebee3ee31c551459","first_computed_at":"2026-07-05T00:28:24.936905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:28:24.936905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XuhPz2HLTOjbA6H7c54aATlC3T+xlbIcQFSxCh+f6FIMqiSfndCsXikpAgXcXeptCqzoeU9HsVXMtfJGgo4aAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:28:24.937390Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.05512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e40d19aef6806304bed720d59b287ad19f423279faf70df1323303923e7c908f","sha256:1e03d7fd2c48e1dbd74dadb33f40477af71db67478308823fbcee7c49979d903"],"state_sha256":"a52150892418a834c4dc122b7531748b6b4465be106bc59e7bf50cab9bf3a27a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PZtmI1mstqB0bFQ5ZoIkrlUZuL+JuRiElxc5oYUR+F39uc7dISWfUe6ibac9owM2acLIgp8dHM6nJV4cmMGHCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:09:30.780172Z","bundle_sha256":"b9314da443470ff7358dcfbdcecaa41215e9edf0802212e0f4e40b42702b792d"}}