{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MHTHYDRIY6TOZ5K3STZ2OT42AY","short_pith_number":"pith:MHTHYDRI","schema_version":"1.0","canonical_sha256":"61e67c0e28c7a6ecf55b94f3a74f9a0607454c2e5ccd3ac4df8d0334c15e207b","source":{"kind":"arxiv","id":"2110.00096","version":1},"attestation_state":"computed","paper":{"title":"Decentralized Graph-Based Multi-Agent Reinforcement Learning Using Reward Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Guannan Qu, Jueming Hu, Weichang Wang, Yongming Liu, Yutian Pang, Zhe Xu","submitted_at":"2021-09-30T21:41:55Z","abstract_excerpt":"In multi-agent reinforcement learning (MARL), it is challenging for a collection of agents to learn complex temporally extended tasks. The difficulties lie in computational complexity and how to learn the high-level ideas behind reward functions. We study the graph-based Markov Decision Process (MDP) where the dynamics of neighboring agents are coupled. We use a reward machine (RM) to encode each agent's task and expose reward function internal structures. RM has the capacity to describe high-level knowledge and encode non-Markovian reward functions. We propose a decentralized learning algorit"},"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":"2110.00096","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2021-09-30T21:41:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8eddf0632c8e45e24f498e6494e16bc9b8e0f87cf548d7a952a16297d4f39622","abstract_canon_sha256":"3ce18befaede49a9bab4e3ae9bf2de0a996feeee2af6d4232a0e4fd91fb6015e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:19:25.555428Z","signature_b64":"JUbv/REGriYQJ2dzXXoL8Vob8qQ/WXMSMpQNq8QxV5UFidN2EtJo6XQWZeJTU19m8WmyeUgT/3329jN3BcXVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61e67c0e28c7a6ecf55b94f3a74f9a0607454c2e5ccd3ac4df8d0334c15e207b","last_reissued_at":"2026-07-05T03:19:25.554938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:19:25.554938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Graph-Based Multi-Agent Reinforcement Learning Using Reward Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Guannan Qu, Jueming Hu, Weichang Wang, Yongming Liu, Yutian Pang, Zhe Xu","submitted_at":"2021-09-30T21:41:55Z","abstract_excerpt":"In multi-agent reinforcement learning (MARL), it is challenging for a collection of agents to learn complex temporally extended tasks. The difficulties lie in computational complexity and how to learn the high-level ideas behind reward functions. We study the graph-based Markov Decision Process (MDP) where the dynamics of neighboring agents are coupled. We use a reward machine (RM) to encode each agent's task and expose reward function internal structures. RM has the capacity to describe high-level knowledge and encode non-Markovian reward functions. We propose a decentralized learning algorit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00096","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/2110.00096/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.00096","created_at":"2026-07-05T03:19:25.554997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.00096v1","created_at":"2026-07-05T03:19:25.554997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00096","created_at":"2026-07-05T03:19:25.554997+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHTHYDRIY6TO","created_at":"2026-07-05T03:19:25.554997+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHTHYDRIY6TOZ5K3","created_at":"2026-07-05T03:19:25.554997+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHTHYDRI","created_at":"2026-07-05T03:19:25.554997+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY","json":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY.json","graph_json":"https://pith.science/api/pith-number/MHTHYDRIY6TOZ5K3STZ2OT42AY/graph.json","events_json":"https://pith.science/api/pith-number/MHTHYDRIY6TOZ5K3STZ2OT42AY/events.json","paper":"https://pith.science/paper/MHTHYDRI"},"agent_actions":{"view_html":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY","download_json":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY.json","view_paper":"https://pith.science/paper/MHTHYDRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.00096&json=true","fetch_graph":"https://pith.science/api/pith-number/MHTHYDRIY6TOZ5K3STZ2OT42AY/graph.json","fetch_events":"https://pith.science/api/pith-number/MHTHYDRIY6TOZ5K3STZ2OT42AY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY/action/storage_attestation","attest_author":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY/action/author_attestation","sign_citation":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY/action/citation_signature","submit_replication":"https://pith.science/pith/MHTHYDRIY6TOZ5K3STZ2OT42AY/action/replication_record"}},"created_at":"2026-07-05T03:19:25.554997+00:00","updated_at":"2026-07-05T03:19:25.554997+00:00"}