{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HOEOHHY2ZPYR2ZFMV3NIEAMXMB","short_pith_number":"pith:HOEOHHY2","canonical_record":{"source":{"id":"1811.12929","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-30T18:29:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4df583bb534390f74c89ab78e1519702d4467cb3f1784e4a28ef506619b605e3","abstract_canon_sha256":"e49f496822effc51d884bde614ac494d1477eaa3d960beeb74b69ea8e4bd6bcd"},"schema_version":"1.0"},"canonical_sha256":"3b88e39f1acbf11d64acaeda820197606d9618fcc484446c43088db2591c9979","source":{"kind":"arxiv","id":"1811.12929","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.12929","created_at":"2026-07-05T02:33:03Z"},{"alias_kind":"arxiv_version","alias_value":"1811.12929v2","created_at":"2026-07-05T02:33:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12929","created_at":"2026-07-05T02:33:03Z"},{"alias_kind":"pith_short_12","alias_value":"HOEOHHY2ZPYR","created_at":"2026-07-05T02:33:03Z"},{"alias_kind":"pith_short_16","alias_value":"HOEOHHY2ZPYR2ZFM","created_at":"2026-07-05T02:33:03Z"},{"alias_kind":"pith_short_8","alias_value":"HOEOHHY2","created_at":"2026-07-05T02:33:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HOEOHHY2ZPYR2ZFMV3NIEAMXMB","target":"record","payload":{"canonical_record":{"source":{"id":"1811.12929","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-30T18:29:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4df583bb534390f74c89ab78e1519702d4467cb3f1784e4a28ef506619b605e3","abstract_canon_sha256":"e49f496822effc51d884bde614ac494d1477eaa3d960beeb74b69ea8e4bd6bcd"},"schema_version":"1.0"},"canonical_sha256":"3b88e39f1acbf11d64acaeda820197606d9618fcc484446c43088db2591c9979","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:03.526280Z","signature_b64":"eJpE3BPaFJjXdZiAG2tFo8Qh+2Pdw1yVPG8bJJ5je9FWycd9cct0aMU3zEtxirY9TAONP8x5p3o+TzN3Xd2PDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b88e39f1acbf11d64acaeda820197606d9618fcc484446c43088db2591c9979","last_reissued_at":"2026-07-05T02:33:03.525774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:03.525774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.12929","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":"2026-07-05T02:33:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N2byFf7AU1x0Pc3LI/H03AudzEDEMLyfbm4ub0a1ryes2BcpvzRY2tUgRcpr2XmWUkS9SsiCgYWXK/o/kcEKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:58:51.819314Z"},"content_sha256":"572a04afb3558f9ccec309a746a703de35acf159b729f9e538a3246149966ce5","schema_version":"1.0","event_id":"sha256:572a04afb3558f9ccec309a746a703de35acf159b729f9e538a3246149966ce5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HOEOHHY2ZPYR2ZFMV3NIEAMXMB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Abstraction with MDP Homomorphisms for Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ondrej Biza, Robert Platt","submitted_at":"2018-11-30T18:29:29Z","abstract_excerpt":"Abstraction of Markov Decision Processes is a useful tool for solving complex problems, as it can ignore unimportant aspects of an environment, simplifying the process of learning an optimal policy. In this paper, we propose a new algorithm for finding abstract MDPs in environments with continuous state spaces. It is based on MDP homomorphisms, a structure-preserving mapping between MDPs. We demonstrate our algorithm's ability to learn abstractions from collected experience and show how to reuse the abstractions to guide exploration in new tasks the agent encounters. Our novel task transfer me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12929","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1811.12929/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:33:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2thOimds2DIdfbJ+U2mX25Q216v1z4gxbn5YMj0olA7OukxUHpTL26u10jNY4fSwNcOfG+T68uVA2FIl7WkMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:58:51.819706Z"},"content_sha256":"dd7f2d5c71a39773b12b5f198d8bc5c1219601fb86d9c2f7639e58a6ddcb769d","schema_version":"1.0","event_id":"sha256:dd7f2d5c71a39773b12b5f198d8bc5c1219601fb86d9c2f7639e58a6ddcb769d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HOEOHHY2ZPYR2ZFMV3NIEAMXMB/bundle.json","state_url":"https://pith.science/pith/HOEOHHY2ZPYR2ZFMV3NIEAMXMB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HOEOHHY2ZPYR2ZFMV3NIEAMXMB/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":"2026-07-07T08:58:51Z","links":{"resolver":"https://pith.science/pith/HOEOHHY2ZPYR2ZFMV3NIEAMXMB","bundle":"https://pith.science/pith/HOEOHHY2ZPYR2ZFMV3NIEAMXMB/bundle.json","state":"https://pith.science/pith/HOEOHHY2ZPYR2ZFMV3NIEAMXMB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HOEOHHY2ZPYR2ZFMV3NIEAMXMB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HOEOHHY2ZPYR2ZFMV3NIEAMXMB","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":"e49f496822effc51d884bde614ac494d1477eaa3d960beeb74b69ea8e4bd6bcd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-30T18:29:29Z","title_canon_sha256":"4df583bb534390f74c89ab78e1519702d4467cb3f1784e4a28ef506619b605e3"},"schema_version":"1.0","source":{"id":"1811.12929","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.12929","created_at":"2026-07-05T02:33:03Z"},{"alias_kind":"arxiv_version","alias_value":"1811.12929v2","created_at":"2026-07-05T02:33:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12929","created_at":"2026-07-05T02:33:03Z"},{"alias_kind":"pith_short_12","alias_value":"HOEOHHY2ZPYR","created_at":"2026-07-05T02:33:03Z"},{"alias_kind":"pith_short_16","alias_value":"HOEOHHY2ZPYR2ZFM","created_at":"2026-07-05T02:33:03Z"},{"alias_kind":"pith_short_8","alias_value":"HOEOHHY2","created_at":"2026-07-05T02:33:03Z"}],"graph_snapshots":[{"event_id":"sha256:dd7f2d5c71a39773b12b5f198d8bc5c1219601fb86d9c2f7639e58a6ddcb769d","target":"graph","created_at":"2026-07-05T02:33:03Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1811.12929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Abstraction of Markov Decision Processes is a useful tool for solving complex problems, as it can ignore unimportant aspects of an environment, simplifying the process of learning an optimal policy. In this paper, we propose a new algorithm for finding abstract MDPs in environments with continuous state spaces. It is based on MDP homomorphisms, a structure-preserving mapping between MDPs. We demonstrate our algorithm's ability to learn abstractions from collected experience and show how to reuse the abstractions to guide exploration in new tasks the agent encounters. Our novel task transfer me","authors_text":"Ondrej Biza, Robert Platt","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-30T18:29:29Z","title":"Online Abstraction with MDP Homomorphisms for Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12929","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":"sha256:572a04afb3558f9ccec309a746a703de35acf159b729f9e538a3246149966ce5","target":"record","created_at":"2026-07-05T02:33:03Z","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":"e49f496822effc51d884bde614ac494d1477eaa3d960beeb74b69ea8e4bd6bcd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-30T18:29:29Z","title_canon_sha256":"4df583bb534390f74c89ab78e1519702d4467cb3f1784e4a28ef506619b605e3"},"schema_version":"1.0","source":{"id":"1811.12929","kind":"arxiv","version":2}},"canonical_sha256":"3b88e39f1acbf11d64acaeda820197606d9618fcc484446c43088db2591c9979","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b88e39f1acbf11d64acaeda820197606d9618fcc484446c43088db2591c9979","first_computed_at":"2026-07-05T02:33:03.525774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:03.525774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eJpE3BPaFJjXdZiAG2tFo8Qh+2Pdw1yVPG8bJJ5je9FWycd9cct0aMU3zEtxirY9TAONP8x5p3o+TzN3Xd2PDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:03.526280Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.12929","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:572a04afb3558f9ccec309a746a703de35acf159b729f9e538a3246149966ce5","sha256:dd7f2d5c71a39773b12b5f198d8bc5c1219601fb86d9c2f7639e58a6ddcb769d"],"state_sha256":"f8eb0c9ef2c306a93dce630e61da94d8d872853615b23d0d0483272d750a1f7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jAp8oWZBE4tjL6aCoVFN+a5SMeGinSknEqWTGgLYHWWOkzAVm1OUdJhfIp4jQG/7ZZOo8wDuzoICHIJ/GPdRCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:58:51.821604Z","bundle_sha256":"ca26fc49df06090e7f59f52152447f1aee8bb965ccd89fc70bba0f5f052effb9"}}