{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:45MZ6NWFT5N6MKPL3VQ35MEYC4","short_pith_number":"pith:45MZ6NWF","schema_version":"1.0","canonical_sha256":"e7599f36c59f5be629ebdd61beb09817060e0738d55e5cb2d901c3c81ece3275","source":{"kind":"arxiv","id":"2302.12232","version":1},"attestation_state":"computed","paper":{"title":"Concept Learning for Interpretable Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Dana Hughes, Joseph Campbell, Katia Sycara, Renos Zabounidis, Simon Stepputtis","submitted_at":"2023-02-23T18:53:09Z","abstract_excerpt":"Multi-agent robotic systems are increasingly operating in real-world environments in close proximity to humans, yet are largely controlled by policy models with inscrutable deep neural network representations. We introduce a method for incorporating interpretable concepts from a domain expert into models trained through multi-agent reinforcement learning, by requiring the model to first predict such concepts then utilize them for decision making. This allows an expert to both reason about the resulting concept policy models in terms of these high-level concepts at run-time, as well as interven"},"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":"2302.12232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-23T18:53:09Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"654c3a15a29f2807ef4ecef3c19036337054921db1b25b01dd32112a3d334b70","abstract_canon_sha256":"9e696d159e96365c6a59a605e931c7d46ab84e57256e6c88d460f863e4a588ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:01.763259Z","signature_b64":"xkHi1wDxHLYfedzPAaS/2G7qkU5v4rOwTvxzfzK3NmOwZm3fLqZuqRn4FiDnNaWXBuyqkSTd/WIeSk/D6ifKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7599f36c59f5be629ebdd61beb09817060e0738d55e5cb2d901c3c81ece3275","last_reissued_at":"2026-07-05T05:45:01.762785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:01.762785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concept Learning for Interpretable Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Dana Hughes, Joseph Campbell, Katia Sycara, Renos Zabounidis, Simon Stepputtis","submitted_at":"2023-02-23T18:53:09Z","abstract_excerpt":"Multi-agent robotic systems are increasingly operating in real-world environments in close proximity to humans, yet are largely controlled by policy models with inscrutable deep neural network representations. We introduce a method for incorporating interpretable concepts from a domain expert into models trained through multi-agent reinforcement learning, by requiring the model to first predict such concepts then utilize them for decision making. This allows an expert to both reason about the resulting concept policy models in terms of these high-level concepts at run-time, as well as interven"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12232","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/2302.12232/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":"2302.12232","created_at":"2026-07-05T05:45:01.762842+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12232v1","created_at":"2026-07-05T05:45:01.762842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12232","created_at":"2026-07-05T05:45:01.762842+00:00"},{"alias_kind":"pith_short_12","alias_value":"45MZ6NWFT5N6","created_at":"2026-07-05T05:45:01.762842+00:00"},{"alias_kind":"pith_short_16","alias_value":"45MZ6NWFT5N6MKPL","created_at":"2026-07-05T05:45:01.762842+00:00"},{"alias_kind":"pith_short_8","alias_value":"45MZ6NWF","created_at":"2026-07-05T05:45:01.762842+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/45MZ6NWFT5N6MKPL3VQ35MEYC4","json":"https://pith.science/pith/45MZ6NWFT5N6MKPL3VQ35MEYC4.json","graph_json":"https://pith.science/api/pith-number/45MZ6NWFT5N6MKPL3VQ35MEYC4/graph.json","events_json":"https://pith.science/api/pith-number/45MZ6NWFT5N6MKPL3VQ35MEYC4/events.json","paper":"https://pith.science/paper/45MZ6NWF"},"agent_actions":{"view_html":"https://pith.science/pith/45MZ6NWFT5N6MKPL3VQ35MEYC4","download_json":"https://pith.science/pith/45MZ6NWFT5N6MKPL3VQ35MEYC4.json","view_paper":"https://pith.science/paper/45MZ6NWF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12232&json=true","fetch_graph":"https://pith.science/api/pith-number/45MZ6NWFT5N6MKPL3VQ35MEYC4/graph.json","fetch_events":"https://pith.science/api/pith-number/45MZ6NWFT5N6MKPL3VQ35MEYC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45MZ6NWFT5N6MKPL3VQ35MEYC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45MZ6NWFT5N6MKPL3VQ35MEYC4/action/storage_attestation","attest_author":"https://pith.science/pith/45MZ6NWFT5N6MKPL3VQ35MEYC4/action/author_attestation","sign_citation":"https://pith.science/pith/45MZ6NWFT5N6MKPL3VQ35MEYC4/action/citation_signature","submit_replication":"https://pith.science/pith/45MZ6NWFT5N6MKPL3VQ35MEYC4/action/replication_record"}},"created_at":"2026-07-05T05:45:01.762842+00:00","updated_at":"2026-07-05T05:45:01.762842+00:00"}