{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3WZNGX77TOP6G7EBFMXQ77CR6P","short_pith_number":"pith:3WZNGX77","canonical_record":{"source":{"id":"1703.08294","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-24T06:35:46Z","cross_cats_sorted":[],"title_canon_sha256":"4e8cdec555cfc206aaa76e50a1b6f51b6fce65eb68b10d378fab5ff2ab7c8a2c","abstract_canon_sha256":"0f633ffaaa3c21adafaf8d52d14decc0bb9e06fcc3d13039faf0b006eb400ed8"},"schema_version":"1.0"},"canonical_sha256":"ddb2d35fff9b9fe37c812b2f0ffc51f3fb8236cc06eb4b01afb5e5b4aadc8d9a","source":{"kind":"arxiv","id":"1703.08294","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.08294","created_at":"2026-05-18T00:33:39Z"},{"alias_kind":"arxiv_version","alias_value":"1703.08294v2","created_at":"2026-05-18T00:33:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08294","created_at":"2026-05-18T00:33:39Z"},{"alias_kind":"pith_short_12","alias_value":"3WZNGX77TOP6","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3WZNGX77TOP6G7EB","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3WZNGX77","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3WZNGX77TOP6G7EBFMXQ77CR6P","target":"record","payload":{"canonical_record":{"source":{"id":"1703.08294","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-24T06:35:46Z","cross_cats_sorted":[],"title_canon_sha256":"4e8cdec555cfc206aaa76e50a1b6f51b6fce65eb68b10d378fab5ff2ab7c8a2c","abstract_canon_sha256":"0f633ffaaa3c21adafaf8d52d14decc0bb9e06fcc3d13039faf0b006eb400ed8"},"schema_version":"1.0"},"canonical_sha256":"ddb2d35fff9b9fe37c812b2f0ffc51f3fb8236cc06eb4b01afb5e5b4aadc8d9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:39.317244Z","signature_b64":"9FqCsibNUV9JJ9fkgZWtim0b+KDZ08bNJjJqXLVoGJmhjiSrHEc5E4nZdmWQoOvRm+JzBTo9GiUneQVC66lUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddb2d35fff9b9fe37c812b2f0ffc51f3fb8236cc06eb4b01afb5e5b4aadc8d9a","last_reissued_at":"2026-05-18T00:33:39.316514Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:39.316514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.08294","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:33:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VStN3WFTLlZBdqx6HgT7hVzy1XwN2oyNgKQzKpYnxSzeQPKOblSqoeAESkIh9V8ZfShNb9bSEAOqAI8rDL7eCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T16:28:38.125573Z"},"content_sha256":"d6d13fa532e739a6f70bfea456c36531f2424cbe7a03c60b49a47448b8d68cff","schema_version":"1.0","event_id":"sha256:d6d13fa532e739a6f70bfea456c36531f2424cbe7a03c60b49a47448b8d68cff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3WZNGX77TOP6G7EBFMXQ77CR6P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Level Discovery of Deep Options","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ion Stoica, Ken Goldberg, Roy Fox, Sanjay Krishnan","submitted_at":"2017-03-24T06:35:46Z","abstract_excerpt":"Augmenting an agent's control with useful higher-level behaviors called options can greatly reduce the sample complexity of reinforcement learning, but manually designing options is infeasible in high-dimensional and abstract state spaces. While recent work has proposed several techniques for automated option discovery, they do not scale to multi-level hierarchies and to expressive representations such as deep networks. We present Discovery of Deep Options (DDO), a policy-gradient algorithm that discovers parametrized options from a set of demonstration trajectories, and can be used recursivel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08294","kind":"arxiv","version":2},"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":"2026-05-18T00:33:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0yawTqtQb34Z90C+R3KCD2YtRA9CViTFAfs/SI8f+ZrhgT07bsrBxR8KVLuKvA8l/eP667mmlfxCi4a6fTt5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T16:28:38.126201Z"},"content_sha256":"9b798c669133e0e9e32c144a173404ac9e6f3722d3f7fff942ab04dcce5ca44c","schema_version":"1.0","event_id":"sha256:9b798c669133e0e9e32c144a173404ac9e6f3722d3f7fff942ab04dcce5ca44c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3WZNGX77TOP6G7EBFMXQ77CR6P/bundle.json","state_url":"https://pith.science/pith/3WZNGX77TOP6G7EBFMXQ77CR6P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3WZNGX77TOP6G7EBFMXQ77CR6P/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":"2026-05-24T16:28:38Z","links":{"resolver":"https://pith.science/pith/3WZNGX77TOP6G7EBFMXQ77CR6P","bundle":"https://pith.science/pith/3WZNGX77TOP6G7EBFMXQ77CR6P/bundle.json","state":"https://pith.science/pith/3WZNGX77TOP6G7EBFMXQ77CR6P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3WZNGX77TOP6G7EBFMXQ77CR6P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3WZNGX77TOP6G7EBFMXQ77CR6P","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":"0f633ffaaa3c21adafaf8d52d14decc0bb9e06fcc3d13039faf0b006eb400ed8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-24T06:35:46Z","title_canon_sha256":"4e8cdec555cfc206aaa76e50a1b6f51b6fce65eb68b10d378fab5ff2ab7c8a2c"},"schema_version":"1.0","source":{"id":"1703.08294","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.08294","created_at":"2026-05-18T00:33:39Z"},{"alias_kind":"arxiv_version","alias_value":"1703.08294v2","created_at":"2026-05-18T00:33:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08294","created_at":"2026-05-18T00:33:39Z"},{"alias_kind":"pith_short_12","alias_value":"3WZNGX77TOP6","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3WZNGX77TOP6G7EB","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3WZNGX77","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:9b798c669133e0e9e32c144a173404ac9e6f3722d3f7fff942ab04dcce5ca44c","target":"graph","created_at":"2026-05-18T00:33:39Z","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":"Augmenting an agent's control with useful higher-level behaviors called options can greatly reduce the sample complexity of reinforcement learning, but manually designing options is infeasible in high-dimensional and abstract state spaces. While recent work has proposed several techniques for automated option discovery, they do not scale to multi-level hierarchies and to expressive representations such as deep networks. We present Discovery of Deep Options (DDO), a policy-gradient algorithm that discovers parametrized options from a set of demonstration trajectories, and can be used recursivel","authors_text":"Ion Stoica, Ken Goldberg, Roy Fox, Sanjay Krishnan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-24T06:35:46Z","title":"Multi-Level Discovery of Deep Options"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08294","kind":"arxiv","version":2},"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:d6d13fa532e739a6f70bfea456c36531f2424cbe7a03c60b49a47448b8d68cff","target":"record","created_at":"2026-05-18T00:33:39Z","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":"0f633ffaaa3c21adafaf8d52d14decc0bb9e06fcc3d13039faf0b006eb400ed8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-24T06:35:46Z","title_canon_sha256":"4e8cdec555cfc206aaa76e50a1b6f51b6fce65eb68b10d378fab5ff2ab7c8a2c"},"schema_version":"1.0","source":{"id":"1703.08294","kind":"arxiv","version":2}},"canonical_sha256":"ddb2d35fff9b9fe37c812b2f0ffc51f3fb8236cc06eb4b01afb5e5b4aadc8d9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddb2d35fff9b9fe37c812b2f0ffc51f3fb8236cc06eb4b01afb5e5b4aadc8d9a","first_computed_at":"2026-05-18T00:33:39.316514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:39.316514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9FqCsibNUV9JJ9fkgZWtim0b+KDZ08bNJjJqXLVoGJmhjiSrHEc5E4nZdmWQoOvRm+JzBTo9GiUneQVC66lUDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:39.317244Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.08294","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6d13fa532e739a6f70bfea456c36531f2424cbe7a03c60b49a47448b8d68cff","sha256:9b798c669133e0e9e32c144a173404ac9e6f3722d3f7fff942ab04dcce5ca44c"],"state_sha256":"6a3b560784b1877e14ad6f957a8fb861d1ee2a770c3de5331cb5144295e737fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jVTk8Fx+qrmNKrNyjVizHKVtry5dMqVXFCn15ZfkHmGR31wxGymasuAJ387djQuVGv9VR3HJqksT1zunH7Z4Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T16:28:38.129755Z","bundle_sha256":"2b9263b9c03a42c5d8fcedd8f0e6914fd12afbce8efef3b8cbbff73d1f1ebe98"}}