{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PAWWFTS2Q3IRYVQULVLXPX7QAQ","short_pith_number":"pith:PAWWFTS2","schema_version":"1.0","canonical_sha256":"782d62ce5a86d11c56145d5777dff00428e1e8c156d4ad34e5320886cd85dc3f","source":{"kind":"arxiv","id":"2002.06473","version":1},"attestation_state":"computed","paper":{"title":"Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Isbell, Yannick Schroecker","submitted_at":"2020-02-15T23:46:29Z","abstract_excerpt":"This work considers two distinct settings: imitation learning and goal-conditioned reinforcement learning. In either case, effective solutions require the agent to reliably reach a specified state (a goal), or set of states (a demonstration). Drawing a connection between probabilistic long-term dynamics and the desired value function, this work introduces an approach which utilizes recent advances in density estimation to effectively learn to reach a given state. As our first contribution, we use this approach for goal-conditioned reinforcement learning and show that it is both efficient and d"},"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":"2002.06473","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-15T23:46:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"39f3f8686915ef42a9c6ad8e3d636a5859a20ce67a907757ac85fcdfa319995e","abstract_canon_sha256":"ad7e4db4e93ee0b15b3f9fada873e25650fa88f6262c754d8f4d0e7443730f6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:41:06.462485Z","signature_b64":"Mf8swtB6YPzXS4EQfd4qLR1QB00zR7rR+HyK3lSvS0BiKnYDIvolldNTE1U0yzBbHqY/bVjvsSDSIDpKAlJCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"782d62ce5a86d11c56145d5777dff00428e1e8c156d4ad34e5320886cd85dc3f","last_reissued_at":"2026-07-05T00:41:06.462021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:41:06.462021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Isbell, Yannick Schroecker","submitted_at":"2020-02-15T23:46:29Z","abstract_excerpt":"This work considers two distinct settings: imitation learning and goal-conditioned reinforcement learning. In either case, effective solutions require the agent to reliably reach a specified state (a goal), or set of states (a demonstration). Drawing a connection between probabilistic long-term dynamics and the desired value function, this work introduces an approach which utilizes recent advances in density estimation to effectively learn to reach a given state. As our first contribution, we use this approach for goal-conditioned reinforcement learning and show that it is both efficient and d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06473","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.06473/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":"2002.06473","created_at":"2026-07-05T00:41:06.462085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.06473v1","created_at":"2026-07-05T00:41:06.462085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06473","created_at":"2026-07-05T00:41:06.462085+00:00"},{"alias_kind":"pith_short_12","alias_value":"PAWWFTS2Q3IR","created_at":"2026-07-05T00:41:06.462085+00:00"},{"alias_kind":"pith_short_16","alias_value":"PAWWFTS2Q3IRYVQU","created_at":"2026-07-05T00:41:06.462085+00:00"},{"alias_kind":"pith_short_8","alias_value":"PAWWFTS2","created_at":"2026-07-05T00:41:06.462085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20350","citing_title":"Decision Flow Policy Optimization","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ","json":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ.json","graph_json":"https://pith.science/api/pith-number/PAWWFTS2Q3IRYVQULVLXPX7QAQ/graph.json","events_json":"https://pith.science/api/pith-number/PAWWFTS2Q3IRYVQULVLXPX7QAQ/events.json","paper":"https://pith.science/paper/PAWWFTS2"},"agent_actions":{"view_html":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ","download_json":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ.json","view_paper":"https://pith.science/paper/PAWWFTS2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.06473&json=true","fetch_graph":"https://pith.science/api/pith-number/PAWWFTS2Q3IRYVQULVLXPX7QAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/PAWWFTS2Q3IRYVQULVLXPX7QAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ/action/storage_attestation","attest_author":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ/action/author_attestation","sign_citation":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ/action/citation_signature","submit_replication":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ/action/replication_record"}},"created_at":"2026-07-05T00:41:06.462085+00:00","updated_at":"2026-07-05T00:41:06.462085+00:00"}