{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DDTD3JGSXM3RN42N2BEEJVSN4O","short_pith_number":"pith:DDTD3JGS","schema_version":"1.0","canonical_sha256":"18e63da4d2bb3716f34dd04844d64de381ff694381067010ae3b137f06075ff8","source":{"kind":"arxiv","id":"1907.03046","version":1},"attestation_state":"computed","paper":{"title":"Learning a Behavioral Repertoire from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniel Cabarcas Jaramillo, Jean-Baptiste Mouret, Miguel Gonzalez Duque, Niels Justesen, Sebastian Risi","submitted_at":"2019-07-05T23:08:08Z","abstract_excerpt":"Imitation Learning (IL) is a machine learning approach to learn a policy from a dataset of demonstrations. IL can be useful to kick-start learning before applying reinforcement learning (RL) but it can also be useful on its own, e.g. to learn to imitate human players in video games. However, a major limitation of current IL approaches is that they learn only a single \"average\" policy based on a dataset that possibly contains demonstrations of numerous different types of behaviors. In this paper, we propose a new approach called Behavioral Repertoire Imitation Learning (BRIL) that instead learn"},"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":"1907.03046","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-05T23:08:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e1b1d3653c2b0581bab56b56eaf4697043db007ff0c6281103f9efe1a1a44677","abstract_canon_sha256":"f418af81acd6f59d83418c49d8026aa5f2ec95d393a3229771c63c20c46dcb82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:19.056417Z","signature_b64":"K1hkRgT3P4McF43RPYws4jLhoKRU0EgugyjCG7kzwsZp2BGWaAWvpk/Txx2PjXEGjVnc4C1xEGFPZ1xOOZyzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18e63da4d2bb3716f34dd04844d64de381ff694381067010ae3b137f06075ff8","last_reissued_at":"2026-05-17T23:41:19.055853Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:19.055853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a Behavioral Repertoire from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniel Cabarcas Jaramillo, Jean-Baptiste Mouret, Miguel Gonzalez Duque, Niels Justesen, Sebastian Risi","submitted_at":"2019-07-05T23:08:08Z","abstract_excerpt":"Imitation Learning (IL) is a machine learning approach to learn a policy from a dataset of demonstrations. IL can be useful to kick-start learning before applying reinforcement learning (RL) but it can also be useful on its own, e.g. to learn to imitate human players in video games. However, a major limitation of current IL approaches is that they learn only a single \"average\" policy based on a dataset that possibly contains demonstrations of numerous different types of behaviors. In this paper, we propose a new approach called Behavioral Repertoire Imitation Learning (BRIL) that instead learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03046","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1907.03046","created_at":"2026-05-17T23:41:19.055955+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.03046v1","created_at":"2026-05-17T23:41:19.055955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03046","created_at":"2026-05-17T23:41:19.055955+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDTD3JGSXM3R","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDTD3JGSXM3RN42N","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDTD3JGS","created_at":"2026-05-18T12:33:15.570797+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/DDTD3JGSXM3RN42N2BEEJVSN4O","json":"https://pith.science/pith/DDTD3JGSXM3RN42N2BEEJVSN4O.json","graph_json":"https://pith.science/api/pith-number/DDTD3JGSXM3RN42N2BEEJVSN4O/graph.json","events_json":"https://pith.science/api/pith-number/DDTD3JGSXM3RN42N2BEEJVSN4O/events.json","paper":"https://pith.science/paper/DDTD3JGS"},"agent_actions":{"view_html":"https://pith.science/pith/DDTD3JGSXM3RN42N2BEEJVSN4O","download_json":"https://pith.science/pith/DDTD3JGSXM3RN42N2BEEJVSN4O.json","view_paper":"https://pith.science/paper/DDTD3JGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.03046&json=true","fetch_graph":"https://pith.science/api/pith-number/DDTD3JGSXM3RN42N2BEEJVSN4O/graph.json","fetch_events":"https://pith.science/api/pith-number/DDTD3JGSXM3RN42N2BEEJVSN4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDTD3JGSXM3RN42N2BEEJVSN4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDTD3JGSXM3RN42N2BEEJVSN4O/action/storage_attestation","attest_author":"https://pith.science/pith/DDTD3JGSXM3RN42N2BEEJVSN4O/action/author_attestation","sign_citation":"https://pith.science/pith/DDTD3JGSXM3RN42N2BEEJVSN4O/action/citation_signature","submit_replication":"https://pith.science/pith/DDTD3JGSXM3RN42N2BEEJVSN4O/action/replication_record"}},"created_at":"2026-05-17T23:41:19.055955+00:00","updated_at":"2026-05-17T23:41:19.055955+00:00"}