{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AOAZSDKLYTCTSVOURIJ33WTC2K","short_pith_number":"pith:AOAZSDKL","schema_version":"1.0","canonical_sha256":"0381990d4bc4c53955d48a13bdda62d2852f8aac07498edd453ec0e2de0c98d2","source":{"kind":"arxiv","id":"2001.00503","version":3},"attestation_state":"computed","paper":{"title":"Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Letian Chen, Matthew Gombolay, Muyleng Ghuy, Rohan Paleja","submitted_at":"2020-01-02T16:04:21Z","abstract_excerpt":"Reinforcement learning (RL) has achieved tremendous success as a general framework for learning how to make decisions. However, this success relies on the interactive hand-tuning of a reward function by RL experts. On the other hand, inverse reinforcement learning (IRL) seeks to learn a reward function from readily-obtained human demonstrations. Yet, IRL suffers from two major limitations: 1) reward ambiguity - there are an infinite number of possible reward functions that could explain an expert's demonstration and 2) heterogeneity - human experts adopt varying strategies and preferences, whi"},"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":"2001.00503","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-02T16:04:21Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"8aff62f8117c8d01404d67924207b71b88aae7256d9d7d61e4be5dbb931724a6","abstract_canon_sha256":"bb2c4f91bef268ed8cd236f5a6438388ecf9b12b84d8478a8c6634d4e8d302bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:36.805593Z","signature_b64":"21G20C1AqJ1Tg2np7Ew7Zno8WjM/asdnjT6nPqW8mKiIfBHRGQTBJHnA9Yua6P9BECl8YUK2+XolocoBzthnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0381990d4bc4c53955d48a13bdda62d2852f8aac07498edd453ec0e2de0c98d2","last_reissued_at":"2026-07-05T01:53:36.805132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:36.805132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Letian Chen, Matthew Gombolay, Muyleng Ghuy, Rohan Paleja","submitted_at":"2020-01-02T16:04:21Z","abstract_excerpt":"Reinforcement learning (RL) has achieved tremendous success as a general framework for learning how to make decisions. However, this success relies on the interactive hand-tuning of a reward function by RL experts. On the other hand, inverse reinforcement learning (IRL) seeks to learn a reward function from readily-obtained human demonstrations. Yet, IRL suffers from two major limitations: 1) reward ambiguity - there are an infinite number of possible reward functions that could explain an expert's demonstration and 2) heterogeneity - human experts adopt varying strategies and preferences, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00503","kind":"arxiv","version":3},"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/2001.00503/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":"2001.00503","created_at":"2026-07-05T01:53:36.805187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.00503v3","created_at":"2026-07-05T01:53:36.805187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00503","created_at":"2026-07-05T01:53:36.805187+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOAZSDKLYTCT","created_at":"2026-07-05T01:53:36.805187+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOAZSDKLYTCTSVOU","created_at":"2026-07-05T01:53:36.805187+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOAZSDKL","created_at":"2026-07-05T01:53:36.805187+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/AOAZSDKLYTCTSVOURIJ33WTC2K","json":"https://pith.science/pith/AOAZSDKLYTCTSVOURIJ33WTC2K.json","graph_json":"https://pith.science/api/pith-number/AOAZSDKLYTCTSVOURIJ33WTC2K/graph.json","events_json":"https://pith.science/api/pith-number/AOAZSDKLYTCTSVOURIJ33WTC2K/events.json","paper":"https://pith.science/paper/AOAZSDKL"},"agent_actions":{"view_html":"https://pith.science/pith/AOAZSDKLYTCTSVOURIJ33WTC2K","download_json":"https://pith.science/pith/AOAZSDKLYTCTSVOURIJ33WTC2K.json","view_paper":"https://pith.science/paper/AOAZSDKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.00503&json=true","fetch_graph":"https://pith.science/api/pith-number/AOAZSDKLYTCTSVOURIJ33WTC2K/graph.json","fetch_events":"https://pith.science/api/pith-number/AOAZSDKLYTCTSVOURIJ33WTC2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOAZSDKLYTCTSVOURIJ33WTC2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOAZSDKLYTCTSVOURIJ33WTC2K/action/storage_attestation","attest_author":"https://pith.science/pith/AOAZSDKLYTCTSVOURIJ33WTC2K/action/author_attestation","sign_citation":"https://pith.science/pith/AOAZSDKLYTCTSVOURIJ33WTC2K/action/citation_signature","submit_replication":"https://pith.science/pith/AOAZSDKLYTCTSVOURIJ33WTC2K/action/replication_record"}},"created_at":"2026-07-05T01:53:36.805187+00:00","updated_at":"2026-07-05T01:53:36.805187+00:00"}