{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:R2ZPHPKBNW6SIB5MU3WBM4J7FM","short_pith_number":"pith:R2ZPHPKB","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"},"canonical_sha256":"8eb2f3bd416dbd2407aca6ec16713f2b34d7092745cd02436aa34917817f34ba","source":{"kind":"arxiv","id":"1806.02813","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.02813","created_at":"2026-05-18T00:13:55Z"},{"alias_kind":"arxiv_version","alias_value":"1806.02813v1","created_at":"2026-05-18T00:13:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02813","created_at":"2026-05-18T00:13:55Z"},{"alias_kind":"pith_short_12","alias_value":"R2ZPHPKBNW6S","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"R2ZPHPKBNW6SIB5M","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"R2ZPHPKB","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:R2ZPHPKBNW6SIB5MU3WBM4J7FM","target":"record","payload":{"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"},"canonical_sha256":"8eb2f3bd416dbd2407aca6ec16713f2b34d7092745cd02436aa34917817f34ba","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"},"source_kind":"arxiv","source_id":"1806.02813","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dFVmwUdMPnGyyVDquFj+GOdh/nYzlr+G2NgpLVyosTxBLbCfMwLGmmgGLPKoXhTtk1RkiGHBV9E0gMvRP2WsAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:24:14.122280Z"},"content_sha256":"72c1bda7f97b137bf1a2e6a39028ef5a6a7682e28ea655e28312a65aa3f926e4","schema_version":"1.0","event_id":"sha256:72c1bda7f97b137bf1a2e6a39028ef5a6a7682e28ea655e28312a65aa3f926e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:R2ZPHPKBNW6SIB5MU3WBM4J7FM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y+aj8LpzFUc8iP9FnIO6N2FeEIGaL6q7ZBWV34gJceh1p53iaCkSepfL+85n4/V/qMI6jw2V+2ZP4rorRPDfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:24:14.122656Z"},"content_sha256":"995472d60bfd68c145d56d9fdbf4e86015ab7220c63b6b3eaa509ffd8e6eaf1f","schema_version":"1.0","event_id":"sha256:995472d60bfd68c145d56d9fdbf4e86015ab7220c63b6b3eaa509ffd8e6eaf1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM/bundle.json","state_url":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T06:24:14Z","links":{"resolver":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM","bundle":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM/bundle.json","state":"https://pith.science/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R2ZPHPKBNW6SIB5MU3WBM4J7FM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:R2ZPHPKBNW6SIB5MU3WBM4J7FM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"84ff9244d9f9df7abae8a46f139de2084351556058495a2ee7570de8af396ee3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-07T17:49:08Z","title_canon_sha256":"875a7b53b0d27658d7b1fec98dbad0c3a83ec937ac377ebb6acdde88cf8f1e24"},"schema_version":"1.0","source":{"id":"1806.02813","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.02813","created_at":"2026-05-18T00:13:55Z"},{"alias_kind":"arxiv_version","alias_value":"1806.02813v1","created_at":"2026-05-18T00:13:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02813","created_at":"2026-05-18T00:13:55Z"},{"alias_kind":"pith_short_12","alias_value":"R2ZPHPKBNW6S","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"R2ZPHPKBNW6SIB5M","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"R2ZPHPKB","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:995472d60bfd68c145d56d9fdbf4e86015ab7220c63b6b3eaa509ffd8e6eaf1f","target":"graph","created_at":"2026-05-18T00:13:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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 ","authors_text":"Abhishek Gupta, Benjamin Eysenbach, John D. Co-Reyes, Pieter Abbeel, Sergey Levine, Yuxuan Liu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-07T17:49:08Z","title":"Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02813","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:72c1bda7f97b137bf1a2e6a39028ef5a6a7682e28ea655e28312a65aa3f926e4","target":"record","created_at":"2026-05-18T00:13:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"84ff9244d9f9df7abae8a46f139de2084351556058495a2ee7570de8af396ee3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-07T17:49:08Z","title_canon_sha256":"875a7b53b0d27658d7b1fec98dbad0c3a83ec937ac377ebb6acdde88cf8f1e24"},"schema_version":"1.0","source":{"id":"1806.02813","kind":"arxiv","version":1}},"canonical_sha256":"8eb2f3bd416dbd2407aca6ec16713f2b34d7092745cd02436aa34917817f34ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8eb2f3bd416dbd2407aca6ec16713f2b34d7092745cd02436aa34917817f34ba","first_computed_at":"2026-05-18T00:13:55.563788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:55.563788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p+QC4yfCXd+rXRtVim1A1Q7eKhCqPT08VgmuQfquJvW9kgopau3MjynmldPxE7fu12T7XQQRSSAp8kge6KRWAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:55.564514Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.02813","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72c1bda7f97b137bf1a2e6a39028ef5a6a7682e28ea655e28312a65aa3f926e4","sha256:995472d60bfd68c145d56d9fdbf4e86015ab7220c63b6b3eaa509ffd8e6eaf1f"],"state_sha256":"edbf8f3d8b376fa17715bec0b796486b218d287b2c914d2bbc010010f71ebf8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WyKkQySYKpXxJi7Sg+bQdlYfpFx9OH/zHUTLBXU2wZbQsq4pX2zBpNzM1JS9aTeLBO7SMLqQw3OcHmLSpX1fBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T06:24:14.124999Z","bundle_sha256":"55237f298ad94d48ce70c4c0df57560f26d11875f4e7863d7d06f2931e7c8aad"}}