{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:R2ZPHPKBNW6SIB5MU3WBM4J7FM","short_pith_number":"pith:R2ZPHPKB","schema_version":"1.0","canonical_sha256":"8eb2f3bd416dbd2407aca6ec16713f2b34d7092745cd02436aa34917817f34ba","source":{"kind":"arxiv","id":"1806.02813","version":1},"attestation_state":"computed","paper":{"title":"Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Benjamin Eysenbach, John D. Co-Reyes, Pieter Abbeel, Sergey Levine, Yuxuan Liu","submitted_at":"2018-06-07T17:49:08Z","abstract_excerpt":"In this work, we take a representation learning perspective on hierarchical reinforcement learning, where the problem of learning lower layers in a hierarchy is transformed into the problem of learning trajectory-level generative models. We show that we can learn continuous latent representations of trajectories, which are effective in solving temporally extended and multi-stage problems. Our proposed model, SeCTAR, draws inspiration from variational autoencoders, and learns latent representations of trajectories. A key component of this method is to learn both a latent-conditioned policy and "},"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":"1806.02813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-07T17:49:08Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"875a7b53b0d27658d7b1fec98dbad0c3a83ec937ac377ebb6acdde88cf8f1e24","abstract_canon_sha256":"84ff9244d9f9df7abae8a46f139de2084351556058495a2ee7570de8af396ee3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:55.564514Z","signature_b64":"p+QC4yfCXd+rXRtVim1A1Q7eKhCqPT08VgmuQfquJvW9kgopau3MjynmldPxE7fu12T7XQQRSSAp8kge6KRWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eb2f3bd416dbd2407aca6ec16713f2b34d7092745cd02436aa34917817f34ba","last_reissued_at":"2026-05-18T00:13:55.563788Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:55.563788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Benjamin Eysenbach, John D. Co-Reyes, Pieter Abbeel, Sergey Levine, Yuxuan Liu","submitted_at":"2018-06-07T17:49:08Z","abstract_excerpt":"In this work, we take a representation learning perspective on hierarchical reinforcement learning, where the problem of learning lower layers in a hierarchy is transformed into the problem of learning trajectory-level generative models. We show that we can learn continuous latent representations of trajectories, which are effective in solving temporally extended and multi-stage problems. Our proposed model, SeCTAR, draws inspiration from variational autoencoders, and learns latent representations of trajectories. A key component of this method is to learn both a latent-conditioned policy and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02813","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":"1806.02813","created_at":"2026-05-18T00:13:55.563904+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.02813v1","created_at":"2026-05-18T00:13:55.563904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02813","created_at":"2026-05-18T00:13:55.563904+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2ZPHPKBNW6S","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2ZPHPKBNW6SIB5M","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2ZPHPKB","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.09237","citing_title":"Shaping Belief States with Generative Environment Models for RL","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00664","citing_title":"Learning World Graphs to Accelerate Hierarchical Reinforcement Learning","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08450","citing_title":"Zero-shot Imitation Learning by Latent Topology Mapping","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM","json":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM.json","graph_json":"https://pith.science/api/pith-number/R2ZPHPKBNW6SIB5MU3WBM4J7FM/graph.json","events_json":"https://pith.science/api/pith-number/R2ZPHPKBNW6SIB5MU3WBM4J7FM/events.json","paper":"https://pith.science/paper/R2ZPHPKB"},"agent_actions":{"view_html":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM","download_json":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM.json","view_paper":"https://pith.science/paper/R2ZPHPKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.02813&json=true","fetch_graph":"https://pith.science/api/pith-number/R2ZPHPKBNW6SIB5MU3WBM4J7FM/graph.json","fetch_events":"https://pith.science/api/pith-number/R2ZPHPKBNW6SIB5MU3WBM4J7FM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM/action/storage_attestation","attest_author":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM/action/author_attestation","sign_citation":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM/action/citation_signature","submit_replication":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM/action/replication_record"}},"created_at":"2026-05-18T00:13:55.563904+00:00","updated_at":"2026-05-18T00:13:55.563904+00:00"}