{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BZKIAICTT5H4MJM6LGO5JRAFZB","short_pith_number":"pith:BZKIAICT","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"},"canonical_sha256":"0e548020539f4fc6259e599dd4c405c8792e6e43bb50b19bdc20754bce959ce0","source":{"kind":"arxiv","id":"1709.06683","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06683","created_at":"2026-05-18T00:29:40Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06683v2","created_at":"2026-05-18T00:29:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06683","created_at":"2026-05-18T00:29:40Z"},{"alias_kind":"pith_short_12","alias_value":"BZKIAICTT5H4","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BZKIAICTT5H4MJM6","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BZKIAICT","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BZKIAICTT5H4MJM6LGO5JRAFZB","target":"record","payload":{"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"},"canonical_sha256":"0e548020539f4fc6259e599dd4c405c8792e6e43bb50b19bdc20754bce959ce0","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"},"source_kind":"arxiv","source_id":"1709.06683","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:29:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3kKt10b4/CAGYjmWEinw+W2HpASj5y8zufrnfvZFkwHl/Fx9+D/px9ZejZANarPuT5MHl0o/a6I23m0DofWACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T21:44:48.553945Z"},"content_sha256":"e8015deddda7dbb0e69c0c534e108645ed2415341bf661c1b00d450ffbbea539","schema_version":"1.0","event_id":"sha256:e8015deddda7dbb0e69c0c534e108645ed2415341bf661c1b00d450ffbbea539"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BZKIAICTT5H4MJM6LGO5JRAFZB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:29:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n2V1EzUdTUCpQSvzNH6H3Wn0HVH4IVfapsQis3wCywMp00Q3YZSwSGSuoHfUHtlA2qwlcbtZc65syN1T1aJGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T21:44:48.554563Z"},"content_sha256":"4d28696ce81543d0f8c8014bf2b6783b1cb37ccc67982e1a4b5f53a7a2d722e5","schema_version":"1.0","event_id":"sha256:4d28696ce81543d0f8c8014bf2b6783b1cb37ccc67982e1a4b5f53a7a2d722e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB/bundle.json","state_url":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BZKIAICTT5H4MJM6LGO5JRAFZB/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":"2026-05-21T21:44:48Z","links":{"resolver":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB","bundle":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB/bundle.json","state":"https://pith.science/pith/BZKIAICTT5H4MJM6LGO5JRAFZB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BZKIAICTT5H4MJM6LGO5JRAFZB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BZKIAICTT5H4MJM6LGO5JRAFZB","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":"0420f4369cc2b1fdb15a8abb96bd67c50ac3afdc32e44b9b226535933d596977","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-20T00:10:52Z","title_canon_sha256":"77c596b22b12a6c657e9da74fab92e3204b474bcd54ecca5ae898b34d5dc3a24"},"schema_version":"1.0","source":{"id":"1709.06683","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06683","created_at":"2026-05-18T00:29:40Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06683v2","created_at":"2026-05-18T00:29:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06683","created_at":"2026-05-18T00:29:40Z"},{"alias_kind":"pith_short_12","alias_value":"BZKIAICTT5H4","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BZKIAICTT5H4MJM6","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BZKIAICT","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:4d28696ce81543d0f8c8014bf2b6783b1cb37ccc67982e1a4b5f53a7a2d722e5","target":"graph","created_at":"2026-05-18T00:29:40Z","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"},"paper":{"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","authors_text":"David Meger, Doina Precup, Joelle Pineau, Peter Henderson, Pierre-Luc Bacon, Wei-Di Chang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-20T00:10:52Z","title":"OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06683","kind":"arxiv","version":2},"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:e8015deddda7dbb0e69c0c534e108645ed2415341bf661c1b00d450ffbbea539","target":"record","created_at":"2026-05-18T00:29:40Z","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":"0420f4369cc2b1fdb15a8abb96bd67c50ac3afdc32e44b9b226535933d596977","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-20T00:10:52Z","title_canon_sha256":"77c596b22b12a6c657e9da74fab92e3204b474bcd54ecca5ae898b34d5dc3a24"},"schema_version":"1.0","source":{"id":"1709.06683","kind":"arxiv","version":2}},"canonical_sha256":"0e548020539f4fc6259e599dd4c405c8792e6e43bb50b19bdc20754bce959ce0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e548020539f4fc6259e599dd4c405c8792e6e43bb50b19bdc20754bce959ce0","first_computed_at":"2026-05-18T00:29:40.726516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:40.726516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7EynKHX5TB1zc/s5dtbjtjpj2n6Zsu/joQ+5UEkaqfjqHjHN8B9rU/Y5ZeDeLHX+qXtqIiChrOeUXhyhldLYAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:40.727484Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.06683","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8015deddda7dbb0e69c0c534e108645ed2415341bf661c1b00d450ffbbea539","sha256:4d28696ce81543d0f8c8014bf2b6783b1cb37ccc67982e1a4b5f53a7a2d722e5"],"state_sha256":"9225d9a6f02c7ad66b5216ac81e49b43499d73354d971af5e4282ce5756cad09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lm+7NzPmfG7snAf5WGK3p2vy2MEnzFwkhcOJUeNs2/g0ZDRH6B01hajXHv2DLLDr5LzLg7fvoaUfATAP5SmrBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T21:44:48.556817Z","bundle_sha256":"a1744dd702d5dca03914ecc6aee6b4b8f7460aa936d62ccd343c06bf1437d973"}}