{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LNTJYRS5LFORH5CFBEE3BSHICE","short_pith_number":"pith:LNTJYRS5","canonical_record":{"source":{"id":"1811.09083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-22T10:15:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"435131c104b7da7d80a337d51c2836339ab0ac652b1f62c14f7d18a93546aac0","abstract_canon_sha256":"b9b1f46a9cf70d4fdead6c03ad06b0809839c6913a20588541be59f08e891e67"},"schema_version":"1.0"},"canonical_sha256":"5b669c465d595d13f4450909b0c8e811110b085d96bf64b4a4af9240252f335d","source":{"kind":"arxiv","id":"1811.09083","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.09083","created_at":"2026-05-18T00:00:07Z"},{"alias_kind":"arxiv_version","alias_value":"1811.09083v1","created_at":"2026-05-18T00:00:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09083","created_at":"2026-05-18T00:00:07Z"},{"alias_kind":"pith_short_12","alias_value":"LNTJYRS5LFOR","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LNTJYRS5LFORH5CF","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LNTJYRS5","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LNTJYRS5LFORH5CFBEE3BSHICE","target":"record","payload":{"canonical_record":{"source":{"id":"1811.09083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-22T10:15:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"435131c104b7da7d80a337d51c2836339ab0ac652b1f62c14f7d18a93546aac0","abstract_canon_sha256":"b9b1f46a9cf70d4fdead6c03ad06b0809839c6913a20588541be59f08e891e67"},"schema_version":"1.0"},"canonical_sha256":"5b669c465d595d13f4450909b0c8e811110b085d96bf64b4a4af9240252f335d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:07.127995Z","signature_b64":"XzdUsToGtmJlouf44kC2+Jkz5+4bM8k5XcEn4DfFzZzNjH0MS6UJ/i7f0WM9k8iUg1d6Jo31sBb/aqbWmJktCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b669c465d595d13f4450909b0c8e811110b085d96bf64b4a4af9240252f335d","last_reissued_at":"2026-05-18T00:00:07.127382Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:07.127382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.09083","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":"2026-05-18T00:00:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IDAQ6LmM+mk3ev9E2663ssntQT8P7jKQl+AumzEg2OHIsGggInH152FHgXPILpgWoHbxSSUJQTj0Nn4qXPIsCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T22:20:25.341059Z"},"content_sha256":"6329b33d075bb87ef30c853d2d6960e8b22b4623931c3cec3185a6803b04d122","schema_version":"1.0","event_id":"sha256:6329b33d075bb87ef30c853d2d6960e8b22b4623931c3cec3185a6803b04d122"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LNTJYRS5LFORH5CFBEE3BSHICE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Szlam, Emily Denton, Rob Fergus, Sainbayar Sukhbaatar","submitted_at":"2018-11-22T10:15:52Z","abstract_excerpt":"In hierarchical reinforcement learning a major challenge is determining appropriate low-level policies. We propose an unsupervised learning scheme, based on asymmetric self-play from Sukhbaatar et al. (2018), that automatically learns a good representation of sub-goals in the environment and a low-level policy that can execute them. A high-level policy can then direct the lower one by generating a sequence of continuous sub-goal vectors. We evaluate our model using Mazebase and Mujoco environments, including the challenging AntGather task. Visualizations of the sub-goal embeddings reveal a log"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09083","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":"2026-05-18T00:00:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"izMEdwN1ryKWXe94LKHR34YvGNc6yjrvePiMWeyMimc4HQzUBp2wPrSBi6/ZL1GKOu8jRUt6MPf7e62Yevw/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T22:20:25.341416Z"},"content_sha256":"1f913d9db1863423f1830addc5d3758fed0ea8be7247abbfc30ba7f7175e8f3d","schema_version":"1.0","event_id":"sha256:1f913d9db1863423f1830addc5d3758fed0ea8be7247abbfc30ba7f7175e8f3d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LNTJYRS5LFORH5CFBEE3BSHICE/bundle.json","state_url":"https://pith.science/pith/LNTJYRS5LFORH5CFBEE3BSHICE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LNTJYRS5LFORH5CFBEE3BSHICE/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":"2026-06-04T22:20:25Z","links":{"resolver":"https://pith.science/pith/LNTJYRS5LFORH5CFBEE3BSHICE","bundle":"https://pith.science/pith/LNTJYRS5LFORH5CFBEE3BSHICE/bundle.json","state":"https://pith.science/pith/LNTJYRS5LFORH5CFBEE3BSHICE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LNTJYRS5LFORH5CFBEE3BSHICE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LNTJYRS5LFORH5CFBEE3BSHICE","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":"b9b1f46a9cf70d4fdead6c03ad06b0809839c6913a20588541be59f08e891e67","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-22T10:15:52Z","title_canon_sha256":"435131c104b7da7d80a337d51c2836339ab0ac652b1f62c14f7d18a93546aac0"},"schema_version":"1.0","source":{"id":"1811.09083","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.09083","created_at":"2026-05-18T00:00:07Z"},{"alias_kind":"arxiv_version","alias_value":"1811.09083v1","created_at":"2026-05-18T00:00:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09083","created_at":"2026-05-18T00:00:07Z"},{"alias_kind":"pith_short_12","alias_value":"LNTJYRS5LFOR","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LNTJYRS5LFORH5CF","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LNTJYRS5","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:1f913d9db1863423f1830addc5d3758fed0ea8be7247abbfc30ba7f7175e8f3d","target":"graph","created_at":"2026-05-18T00:00:07Z","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 hierarchical reinforcement learning a major challenge is determining appropriate low-level policies. We propose an unsupervised learning scheme, based on asymmetric self-play from Sukhbaatar et al. (2018), that automatically learns a good representation of sub-goals in the environment and a low-level policy that can execute them. A high-level policy can then direct the lower one by generating a sequence of continuous sub-goal vectors. We evaluate our model using Mazebase and Mujoco environments, including the challenging AntGather task. Visualizations of the sub-goal embeddings reveal a log","authors_text":"Arthur Szlam, Emily Denton, Rob Fergus, Sainbayar Sukhbaatar","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-22T10:15:52Z","title":"Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09083","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":"sha256:6329b33d075bb87ef30c853d2d6960e8b22b4623931c3cec3185a6803b04d122","target":"record","created_at":"2026-05-18T00:00:07Z","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":"b9b1f46a9cf70d4fdead6c03ad06b0809839c6913a20588541be59f08e891e67","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-22T10:15:52Z","title_canon_sha256":"435131c104b7da7d80a337d51c2836339ab0ac652b1f62c14f7d18a93546aac0"},"schema_version":"1.0","source":{"id":"1811.09083","kind":"arxiv","version":1}},"canonical_sha256":"5b669c465d595d13f4450909b0c8e811110b085d96bf64b4a4af9240252f335d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b669c465d595d13f4450909b0c8e811110b085d96bf64b4a4af9240252f335d","first_computed_at":"2026-05-18T00:00:07.127382Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:07.127382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XzdUsToGtmJlouf44kC2+Jkz5+4bM8k5XcEn4DfFzZzNjH0MS6UJ/i7f0WM9k8iUg1d6Jo31sBb/aqbWmJktCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:07.127995Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.09083","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6329b33d075bb87ef30c853d2d6960e8b22b4623931c3cec3185a6803b04d122","sha256:1f913d9db1863423f1830addc5d3758fed0ea8be7247abbfc30ba7f7175e8f3d"],"state_sha256":"4c5b64fded5c56d45f16d616a1acff53e39a5f53dedddf7db4a043b2975bd38a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OjKiOznBq8IKHPZuslR7PDS+mQlLBGvUBAeysq0ZhH1Gk/cRlWk19lQDa+hlLz0lA3FEveNgGU+GeKn5ZhwgAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T22:20:25.343349Z","bundle_sha256":"5310850f271f2b467468e587a4f788a571bb64d3d75e31f663cc1f60c682a973"}}