{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:RG6N37JYQDAPTKYSWDPYMIMFT4","short_pith_number":"pith:RG6N37JY","canonical_record":{"source":{"id":"1608.03694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-08-12T07:26:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6c50b287b368eacabeae98bca5be9439c0e88d8ed8cf01575ddcd91a20785a96","abstract_canon_sha256":"1631f6958aaa1a407d29643e3dc6e50d7e58e9ba0e1014c049ecdae1c9f67784"},"schema_version":"1.0"},"canonical_sha256":"89bcddfd3880c0f9ab12b0df8621859f129ab94513b60c166f4cc4867777e1c5","source":{"kind":"arxiv","id":"1608.03694","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.03694","created_at":"2026-05-18T01:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"1608.03694v1","created_at":"2026-05-18T01:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.03694","created_at":"2026-05-18T01:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"RG6N37JYQDAP","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RG6N37JYQDAPTKYS","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RG6N37JY","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:RG6N37JYQDAPTKYSWDPYMIMFT4","target":"record","payload":{"canonical_record":{"source":{"id":"1608.03694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-08-12T07:26:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6c50b287b368eacabeae98bca5be9439c0e88d8ed8cf01575ddcd91a20785a96","abstract_canon_sha256":"1631f6958aaa1a407d29643e3dc6e50d7e58e9ba0e1014c049ecdae1c9f67784"},"schema_version":"1.0"},"canonical_sha256":"89bcddfd3880c0f9ab12b0df8621859f129ab94513b60c166f4cc4867777e1c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:37.612498Z","signature_b64":"DvmNq2BNANZ01dd2VCvMVyR8R4TK8WDbL/P2pOlWac2Cqp/7PLLp16YoXZfhz4jTEhERwBe52i0wkOGoJ3FlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89bcddfd3880c0f9ab12b0df8621859f129ab94513b60c166f4cc4867777e1c5","last_reissued_at":"2026-05-18T01:03:37.611905Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:37.611905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.03694","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V9EZsh/pJchHC9IMrm1LwHlZ8YU0m8HLQhS3iwhFgG8ZHbZiVqc/bqM2TPGXYjYzXT58WJN6SI2C+rwqqSKYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:04:27.801210Z"},"content_sha256":"5d7984cfb2d4d61be475d640301e4a6418d6f8c981cbead9a143796d161c0723","schema_version":"1.0","event_id":"sha256:5d7984cfb2d4d61be475d640301e4a6418d6f8c981cbead9a143796d161c0723"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:RG6N37JYQDAPTKYSWDPYMIMFT4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Density Matching Reward Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Andy Park, Kyungjae Lee, Songhwai Oh, Sungjoon Choi","submitted_at":"2016-08-12T07:26:59Z","abstract_excerpt":"In this paper, we focus on the problem of inferring the underlying reward function of an expert given demonstrations, which is often referred to as inverse reinforcement learning (IRL). In particular, we propose a model-free density-based IRL algorithm, named density matching reward learning (DMRL), which does not require model dynamics. The performance of DMRL is analyzed theoretically and the sample complexity is derived. Furthermore, the proposed DMRL is extended to handle nonlinear IRL problems by assuming that the reward function is in the reproducing kernel Hilbert space (RKHS) and kerne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.03694","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v5ccVk2cWceyeSiR1A1CB7wQOf69pdoS7UHFIh3W9+W0LQFP7BmRB98WJlDl6JOIqWXfAzWNugEPSfbqyKSZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:04:27.801626Z"},"content_sha256":"3332fdde04910f4976bb57150993950dd4c82d470e3653e9d35727b098880c68","schema_version":"1.0","event_id":"sha256:3332fdde04910f4976bb57150993950dd4c82d470e3653e9d35727b098880c68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RG6N37JYQDAPTKYSWDPYMIMFT4/bundle.json","state_url":"https://pith.science/pith/RG6N37JYQDAPTKYSWDPYMIMFT4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RG6N37JYQDAPTKYSWDPYMIMFT4/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":"2026-05-28T20:04:27Z","links":{"resolver":"https://pith.science/pith/RG6N37JYQDAPTKYSWDPYMIMFT4","bundle":"https://pith.science/pith/RG6N37JYQDAPTKYSWDPYMIMFT4/bundle.json","state":"https://pith.science/pith/RG6N37JYQDAPTKYSWDPYMIMFT4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RG6N37JYQDAPTKYSWDPYMIMFT4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:RG6N37JYQDAPTKYSWDPYMIMFT4","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":"1631f6958aaa1a407d29643e3dc6e50d7e58e9ba0e1014c049ecdae1c9f67784","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-08-12T07:26:59Z","title_canon_sha256":"6c50b287b368eacabeae98bca5be9439c0e88d8ed8cf01575ddcd91a20785a96"},"schema_version":"1.0","source":{"id":"1608.03694","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.03694","created_at":"2026-05-18T01:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"1608.03694v1","created_at":"2026-05-18T01:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.03694","created_at":"2026-05-18T01:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"RG6N37JYQDAP","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RG6N37JYQDAPTKYS","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RG6N37JY","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:3332fdde04910f4976bb57150993950dd4c82d470e3653e9d35727b098880c68","target":"graph","created_at":"2026-05-18T01:03:37Z","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":"In this paper, we focus on the problem of inferring the underlying reward function of an expert given demonstrations, which is often referred to as inverse reinforcement learning (IRL). In particular, we propose a model-free density-based IRL algorithm, named density matching reward learning (DMRL), which does not require model dynamics. The performance of DMRL is analyzed theoretically and the sample complexity is derived. Furthermore, the proposed DMRL is extended to handle nonlinear IRL problems by assuming that the reward function is in the reproducing kernel Hilbert space (RKHS) and kerne","authors_text":"Andy Park, Kyungjae Lee, Songhwai Oh, Sungjoon Choi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-08-12T07:26:59Z","title":"Density Matching Reward Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.03694","kind":"arxiv","version":1},"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":"sha256:5d7984cfb2d4d61be475d640301e4a6418d6f8c981cbead9a143796d161c0723","target":"record","created_at":"2026-05-18T01:03:37Z","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":"1631f6958aaa1a407d29643e3dc6e50d7e58e9ba0e1014c049ecdae1c9f67784","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-08-12T07:26:59Z","title_canon_sha256":"6c50b287b368eacabeae98bca5be9439c0e88d8ed8cf01575ddcd91a20785a96"},"schema_version":"1.0","source":{"id":"1608.03694","kind":"arxiv","version":1}},"canonical_sha256":"89bcddfd3880c0f9ab12b0df8621859f129ab94513b60c166f4cc4867777e1c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89bcddfd3880c0f9ab12b0df8621859f129ab94513b60c166f4cc4867777e1c5","first_computed_at":"2026-05-18T01:03:37.611905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:37.611905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DvmNq2BNANZ01dd2VCvMVyR8R4TK8WDbL/P2pOlWac2Cqp/7PLLp16YoXZfhz4jTEhERwBe52i0wkOGoJ3FlAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:37.612498Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.03694","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d7984cfb2d4d61be475d640301e4a6418d6f8c981cbead9a143796d161c0723","sha256:3332fdde04910f4976bb57150993950dd4c82d470e3653e9d35727b098880c68"],"state_sha256":"1ddf03b95c36ed363dc7f97552c53548b203b35ee59481b4b99afe165180cad0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q9QSW5ot2Qdus6lWW0EjGyeXdfsd1kQqL62SPqQVrmUiqhQvexo7H1vl3QSjgIBu6uFLCAS1hriLQ5+ol30aCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T20:04:27.804648Z","bundle_sha256":"2d135b28185cde703abbccdca6080fb528404368ce9118f3b1c1d24ce349849a"}}