{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BZKIAICTT5H4MJM6LGO5JRAFZB","short_pith_number":"pith:BZKIAICT","schema_version":"1.0","canonical_sha256":"0e548020539f4fc6259e599dd4c405c8792e6e43bb50b19bdc20754bce959ce0","source":{"kind":"arxiv","id":"1709.06683","version":2},"attestation_state":"computed","paper":{"title":"OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Meger, Doina Precup, Joelle Pineau, Peter Henderson, Pierre-Luc Bacon, Wei-Di Chang","submitted_at":"2017-09-20T00:10:52Z","abstract_excerpt":"Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a useful paradigm to learn the underlying reward function directly from expert demonstrations. Yet in reality, the corpus of demonstrations may contain trajectories arising from a diverse set of underlying reward functions rather than a single one. Thus, in inverse reinforcement learning, it is useful to consider such a decomposition. The options framework in rei"},"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":"1709.06683","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-20T00:10:52Z","cross_cats_sorted":[],"title_canon_sha256":"77c596b22b12a6c657e9da74fab92e3204b474bcd54ecca5ae898b34d5dc3a24","abstract_canon_sha256":"0420f4369cc2b1fdb15a8abb96bd67c50ac3afdc32e44b9b226535933d596977"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:40.727484Z","signature_b64":"7EynKHX5TB1zc/s5dtbjtjpj2n6Zsu/joQ+5UEkaqfjqHjHN8B9rU/Y5ZeDeLHX+qXtqIiChrOeUXhyhldLYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e548020539f4fc6259e599dd4c405c8792e6e43bb50b19bdc20754bce959ce0","last_reissued_at":"2026-05-18T00:29:40.726516Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:40.726516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Meger, Doina Precup, Joelle Pineau, Peter Henderson, Pierre-Luc Bacon, Wei-Di Chang","submitted_at":"2017-09-20T00:10:52Z","abstract_excerpt":"Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a useful paradigm to learn the underlying reward function directly from expert demonstrations. Yet in reality, the corpus of demonstrations may contain trajectories arising from a diverse set of underlying reward functions rather than a single one. Thus, in inverse reinforcement learning, it is useful to consider such a decomposition. The options framework in rei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06683","kind":"arxiv","version":2},"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":"1709.06683","created_at":"2026-05-18T00:29:40.726679+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.06683v2","created_at":"2026-05-18T00:29:40.726679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06683","created_at":"2026-05-18T00:29:40.726679+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZKIAICTT5H4","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZKIAICTT5H4MJM6","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZKIAICT","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08902","citing_title":"Intention-Conditioned Flow Occupancy Models","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB","json":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB.json","graph_json":"https://pith.science/api/pith-number/BZKIAICTT5H4MJM6LGO5JRAFZB/graph.json","events_json":"https://pith.science/api/pith-number/BZKIAICTT5H4MJM6LGO5JRAFZB/events.json","paper":"https://pith.science/paper/BZKIAICT"},"agent_actions":{"view_html":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB","download_json":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB.json","view_paper":"https://pith.science/paper/BZKIAICT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.06683&json=true","fetch_graph":"https://pith.science/api/pith-number/BZKIAICTT5H4MJM6LGO5JRAFZB/graph.json","fetch_events":"https://pith.science/api/pith-number/BZKIAICTT5H4MJM6LGO5JRAFZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB/action/storage_attestation","attest_author":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB/action/author_attestation","sign_citation":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB/action/citation_signature","submit_replication":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB/action/replication_record"}},"created_at":"2026-05-18T00:29:40.726679+00:00","updated_at":"2026-05-18T00:29:40.726679+00:00"}