{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6XP6OZX5PDZH6RBXLNPDX4U2RJ","short_pith_number":"pith:6XP6OZX5","schema_version":"1.0","canonical_sha256":"f5dfe766fd78f27f44375b5e3bf29a8a485bbe2c17501fc0488c4bd71afc591d","source":{"kind":"arxiv","id":"1912.06088","version":4},"attestation_state":"computed","paper":{"title":"Learning to Reach Goals via Iterated Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Ashwin Reddy, Benjamin Eysenbach, Coline Devin, Dibya Ghosh, Justin Fu, Sergey Levine","submitted_at":"2019-12-12T17:26:47Z","abstract_excerpt":"Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it requires access to demonstrations from a human supervisor. In this paper, we study RL algorithms that use imitation learning to acquire goal reaching policies from scratch, without the need for expert demonstrations or a value function. In lieu of demonstrations, we leverage the property that any trajectory is a successful demonstration for reaching the final "},"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":"1912.06088","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T17:26:47Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"06072c03dad2437efdef1c5e00a2f6ad82463aa0660253b3133c286bf46d203f","abstract_canon_sha256":"9db490dc2645d6ec044d34d0a6d99d6a0dcb2ed4ac2b9a6581b22e5d922fb5cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:55.327247Z","signature_b64":"n+9gWXlBPwrjE9AY2k7u+rNb5Wh2oLi4XrISZlLnOlKPSjFR+UN7vYUTDkLmZW8PInTeCKM5lmKpwKuRYN3cCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5dfe766fd78f27f44375b5e3bf29a8a485bbe2c17501fc0488c4bd71afc591d","last_reissued_at":"2026-07-05T01:39:55.326831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:55.326831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Reach Goals via Iterated Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Ashwin Reddy, Benjamin Eysenbach, Coline Devin, Dibya Ghosh, Justin Fu, Sergey Levine","submitted_at":"2019-12-12T17:26:47Z","abstract_excerpt":"Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it requires access to demonstrations from a human supervisor. In this paper, we study RL algorithms that use imitation learning to acquire goal reaching policies from scratch, without the need for expert demonstrations or a value function. In lieu of demonstrations, we leverage the property that any trajectory is a successful demonstration for reaching the final "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.06088","kind":"arxiv","version":4},"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/1912.06088/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":"1912.06088","created_at":"2026-07-05T01:39:55.326895+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.06088v4","created_at":"2026-07-05T01:39:55.326895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.06088","created_at":"2026-07-05T01:39:55.326895+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XP6OZX5PDZH","created_at":"2026-07-05T01:39:55.326895+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XP6OZX5PDZH6RBX","created_at":"2026-07-05T01:39:55.326895+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XP6OZX5","created_at":"2026-07-05T01:39:55.326895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21646","citing_title":"Energy-based Compositional Diffusion Planning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09476","citing_title":"Goal Sets, Not Goal States: Queryable Robot Goals through Goal-Set Hindsight Relabeling","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23551","citing_title":"Goal-Conditioned Agents that Learn Everything All at Once","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21800","citing_title":"stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2106.01345","citing_title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19312","citing_title":"LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09364","citing_title":"Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22724","citing_title":"GCImOpt: Learning efficient goal-conditioned policies by imitating optimal trajectories","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03075","citing_title":"Refining Compositional Diffusion for Reliable Long-Horizon Planning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11137","citing_title":"From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08960","citing_title":"Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07278","citing_title":"Predictive but Not Plannable: RC-aux for Latent World Models","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ","json":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ.json","graph_json":"https://pith.science/api/pith-number/6XP6OZX5PDZH6RBXLNPDX4U2RJ/graph.json","events_json":"https://pith.science/api/pith-number/6XP6OZX5PDZH6RBXLNPDX4U2RJ/events.json","paper":"https://pith.science/paper/6XP6OZX5"},"agent_actions":{"view_html":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ","download_json":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ.json","view_paper":"https://pith.science/paper/6XP6OZX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.06088&json=true","fetch_graph":"https://pith.science/api/pith-number/6XP6OZX5PDZH6RBXLNPDX4U2RJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6XP6OZX5PDZH6RBXLNPDX4U2RJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ/action/storage_attestation","attest_author":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ/action/author_attestation","sign_citation":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ/action/citation_signature","submit_replication":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ/action/replication_record"}},"created_at":"2026-07-05T01:39:55.326895+00:00","updated_at":"2026-07-05T01:39:55.326895+00:00"}