{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PPGQRCMY3UMKK3FNP5QIZFNKJV","short_pith_number":"pith:PPGQRCMY","schema_version":"1.0","canonical_sha256":"7bcd088998dd18a56cad7f608c95aa4d530b915abc030376ae39ae8299de8751","source":{"kind":"arxiv","id":"1811.11359","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Control Through Non-Parametric Discriminative Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Catalin Ionescu, David Warde-Farley, Steven Hansen, Tejas Kulkarni, Tom Van de Wiele, Volodymyr Mnih","submitted_at":"2018-11-28T02:35:24Z","abstract_excerpt":"Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve perceptually-specified goals using only a stream of observations and actions. Our agent simultaneously learns a goal-conditioned policy and a goal achievement reward function that measures how similar a state is to the goal state. This dual optimization leads to a co-operative game, giving rise to a learned reward function that reflects similarity in controllable asp"},"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":"1811.11359","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-28T02:35:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d35d0aa5a9a8377758d80c8d98ed88e1aadd401bede4bc759ddc140039f0f474","abstract_canon_sha256":"d2cf23a577c8a3f8e009a502704962a9b1e7160686149fa51d8984639addbadd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:44.118885Z","signature_b64":"rZtb3hJTX6ErqG8EbxbujPJ6pkehCDPm11VmX1iiN3zWTdXZw5Q1I4vb1rYonLBdgwY22VmClidzJEOPVi23Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bcd088998dd18a56cad7f608c95aa4d530b915abc030376ae39ae8299de8751","last_reissued_at":"2026-05-17T23:59:44.118471Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:44.118471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Control Through Non-Parametric Discriminative Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Catalin Ionescu, David Warde-Farley, Steven Hansen, Tejas Kulkarni, Tom Van de Wiele, Volodymyr Mnih","submitted_at":"2018-11-28T02:35:24Z","abstract_excerpt":"Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve perceptually-specified goals using only a stream of observations and actions. Our agent simultaneously learns a goal-conditioned policy and a goal achievement reward function that measures how similar a state is to the goal state. This dual optimization leads to a co-operative game, giving rise to a learned reward function that reflects similarity in controllable asp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11359","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1811.11359","created_at":"2026-05-17T23:59:44.118534+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.11359v1","created_at":"2026-05-17T23:59:44.118534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11359","created_at":"2026-05-17T23:59:44.118534+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPGQRCMY3UMK","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPGQRCMY3UMKK3FN","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPGQRCMY","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2506.21039","citing_title":"Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2409.12917","citing_title":"Training Language Models to Self-Correct via Reinforcement Learning","ref_index":296,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06145","citing_title":"Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":212,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV","json":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV.json","graph_json":"https://pith.science/api/pith-number/PPGQRCMY3UMKK3FNP5QIZFNKJV/graph.json","events_json":"https://pith.science/api/pith-number/PPGQRCMY3UMKK3FNP5QIZFNKJV/events.json","paper":"https://pith.science/paper/PPGQRCMY"},"agent_actions":{"view_html":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV","download_json":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV.json","view_paper":"https://pith.science/paper/PPGQRCMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.11359&json=true","fetch_graph":"https://pith.science/api/pith-number/PPGQRCMY3UMKK3FNP5QIZFNKJV/graph.json","fetch_events":"https://pith.science/api/pith-number/PPGQRCMY3UMKK3FNP5QIZFNKJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV/action/storage_attestation","attest_author":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV/action/author_attestation","sign_citation":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV/action/citation_signature","submit_replication":"https://pith.science/pith/PPGQRCMY3UMKK3FNP5QIZFNKJV/action/replication_record"}},"created_at":"2026-05-17T23:59:44.118534+00:00","updated_at":"2026-05-17T23:59:44.118534+00:00"}