{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:52JR544R4FX55SHHGBGYH2M4NQ","short_pith_number":"pith:52JR544R","canonical_record":{"source":{"id":"1703.00956","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-02T21:31:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3213c85d1c9c79e6e5fd6dca52809f49d30b29e85d387a96d451ca0c94146c1","abstract_canon_sha256":"840b6526d526b9a06477e866aa10e33045df6631d94847dff9f2369e41671b71"},"schema_version":"1.0"},"canonical_sha256":"ee931ef391e16fdec8e7304d83e99c6c1b77135d3aef2ffd2bc3b09e73e2c8c8","source":{"kind":"arxiv","id":"1703.00956","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.00956","created_at":"2026-05-18T00:42:17Z"},{"alias_kind":"arxiv_version","alias_value":"1703.00956v2","created_at":"2026-05-18T00:42:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00956","created_at":"2026-05-18T00:42:17Z"},{"alias_kind":"pith_short_12","alias_value":"52JR544R4FX5","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"52JR544R4FX55SHH","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"52JR544R","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:52JR544R4FX55SHHGBGYH2M4NQ","target":"record","payload":{"canonical_record":{"source":{"id":"1703.00956","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-02T21:31:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3213c85d1c9c79e6e5fd6dca52809f49d30b29e85d387a96d451ca0c94146c1","abstract_canon_sha256":"840b6526d526b9a06477e866aa10e33045df6631d94847dff9f2369e41671b71"},"schema_version":"1.0"},"canonical_sha256":"ee931ef391e16fdec8e7304d83e99c6c1b77135d3aef2ffd2bc3b09e73e2c8c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:17.308579Z","signature_b64":"f0YV4Ir3Xrk9PEbXUfzG/yur1v7lRfd2VkIXF9WAVn38tfAINaTHI4eGNisbP+JsgRRCko3x5oPikw38dqJhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee931ef391e16fdec8e7304d83e99c6c1b77135d3aef2ffd2bc3b09e73e2c8c8","last_reissued_at":"2026-05-18T00:42:17.307908Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:17.307908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.00956","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":"2026-05-18T00:42:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZjWj+FzawHPobefaksLlSQyg2UADsLX8jHypLJ3TTsQIiuof2KhVxw/x80G/Am+z6bKpxTrr5nAFbDJKwJSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:17:54.536010Z"},"content_sha256":"441ebc8172309a0fa52eb6046b678825c7346452adaa8984e19678299daa7ef1","schema_version":"1.0","event_id":"sha256:441ebc8172309a0fa52eb6046b678825c7346452adaa8984e19678299daa7ef1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:52JR544R4FX55SHHGBGYH2M4NQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Laplacian Framework for Option Discovery in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Marc G. Bellemare, Marlos C. Machado, Michael Bowling","submitted_at":"2017-03-02T21:31:29Z","abstract_excerpt":"Representation learning and option discovery are two of the biggest challenges in reinforcement learning (RL). Proto-value functions (PVFs) are a well-known approach for representation learning in MDPs. In this paper we address the option discovery problem by showing how PVFs implicitly define options. We do it by introducing eigenpurposes, intrinsic reward functions derived from the learned representations. The options discovered from eigenpurposes traverse the principal directions of the state space. They are useful for multiple tasks because they are discovered without taking the environmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00956","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":"2026-05-18T00:42:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ec2DoXqo0WFU0dtqSh29aBXmrVUQrStj2HaMmkRCQrGWCc3phjNicQojJeeaAf17hiZLfoAHuMXPOdndMLooAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:17:54.536378Z"},"content_sha256":"a3bbfb2d6a9ca28b603379183929f8d7b12db88c02b721c7573c809d2326982a","schema_version":"1.0","event_id":"sha256:a3bbfb2d6a9ca28b603379183929f8d7b12db88c02b721c7573c809d2326982a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/52JR544R4FX55SHHGBGYH2M4NQ/bundle.json","state_url":"https://pith.science/pith/52JR544R4FX55SHHGBGYH2M4NQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/52JR544R4FX55SHHGBGYH2M4NQ/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":"2026-05-28T00:17:54Z","links":{"resolver":"https://pith.science/pith/52JR544R4FX55SHHGBGYH2M4NQ","bundle":"https://pith.science/pith/52JR544R4FX55SHHGBGYH2M4NQ/bundle.json","state":"https://pith.science/pith/52JR544R4FX55SHHGBGYH2M4NQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/52JR544R4FX55SHHGBGYH2M4NQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:52JR544R4FX55SHHGBGYH2M4NQ","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":"840b6526d526b9a06477e866aa10e33045df6631d94847dff9f2369e41671b71","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-02T21:31:29Z","title_canon_sha256":"e3213c85d1c9c79e6e5fd6dca52809f49d30b29e85d387a96d451ca0c94146c1"},"schema_version":"1.0","source":{"id":"1703.00956","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.00956","created_at":"2026-05-18T00:42:17Z"},{"alias_kind":"arxiv_version","alias_value":"1703.00956v2","created_at":"2026-05-18T00:42:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00956","created_at":"2026-05-18T00:42:17Z"},{"alias_kind":"pith_short_12","alias_value":"52JR544R4FX5","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"52JR544R4FX55SHH","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"52JR544R","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:a3bbfb2d6a9ca28b603379183929f8d7b12db88c02b721c7573c809d2326982a","target":"graph","created_at":"2026-05-18T00:42:17Z","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":"Representation learning and option discovery are two of the biggest challenges in reinforcement learning (RL). Proto-value functions (PVFs) are a well-known approach for representation learning in MDPs. In this paper we address the option discovery problem by showing how PVFs implicitly define options. We do it by introducing eigenpurposes, intrinsic reward functions derived from the learned representations. The options discovered from eigenpurposes traverse the principal directions of the state space. They are useful for multiple tasks because they are discovered without taking the environmen","authors_text":"Marc G. Bellemare, Marlos C. Machado, Michael Bowling","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-02T21:31:29Z","title":"A Laplacian Framework for Option Discovery in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00956","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":"sha256:441ebc8172309a0fa52eb6046b678825c7346452adaa8984e19678299daa7ef1","target":"record","created_at":"2026-05-18T00:42:17Z","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":"840b6526d526b9a06477e866aa10e33045df6631d94847dff9f2369e41671b71","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-02T21:31:29Z","title_canon_sha256":"e3213c85d1c9c79e6e5fd6dca52809f49d30b29e85d387a96d451ca0c94146c1"},"schema_version":"1.0","source":{"id":"1703.00956","kind":"arxiv","version":2}},"canonical_sha256":"ee931ef391e16fdec8e7304d83e99c6c1b77135d3aef2ffd2bc3b09e73e2c8c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee931ef391e16fdec8e7304d83e99c6c1b77135d3aef2ffd2bc3b09e73e2c8c8","first_computed_at":"2026-05-18T00:42:17.307908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:17.307908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f0YV4Ir3Xrk9PEbXUfzG/yur1v7lRfd2VkIXF9WAVn38tfAINaTHI4eGNisbP+JsgRRCko3x5oPikw38dqJhAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:17.308579Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.00956","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:441ebc8172309a0fa52eb6046b678825c7346452adaa8984e19678299daa7ef1","sha256:a3bbfb2d6a9ca28b603379183929f8d7b12db88c02b721c7573c809d2326982a"],"state_sha256":"6f93aacd4a985df2153350bb68f225837d5acb5b19de771ce225683c03f33b95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rrL9eo3dlMmakGgU4Ca0mjmXZY9MXxP5a+BoepD8Caa5J2+mqQoqshzFAYOfDOdNnPOalLvFvUlOn9lKmauJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T00:17:54.538752Z","bundle_sha256":"c50836e0a2fcdb9fa51e73a8a32fd078711c596141b70eae89b941350b72118a"}}