{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FAYME62XG52LVCGAIPFFOVWUI7","short_pith_number":"pith:FAYME62X","canonical_record":{"source":{"id":"2205.13950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T12:49:33Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"370d0e73269487c169ab480ca0176d87e7f5362ec18f44fa21a8c0125a97644f","abstract_canon_sha256":"645a251a042d3e0982798998dfaf5405b863f30d2dc526d5f759b9524c199c74"},"schema_version":"1.0"},"canonical_sha256":"2830c27b573774ba88c043ca5756d447ce248028445e57539abf1bad1c2ae955","source":{"kind":"arxiv","id":"2205.13950","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13950","created_at":"2026-07-05T04:26:54Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13950v1","created_at":"2026-07-05T04:26:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13950","created_at":"2026-07-05T04:26:54Z"},{"alias_kind":"pith_short_12","alias_value":"FAYME62XG52L","created_at":"2026-07-05T04:26:54Z"},{"alias_kind":"pith_short_16","alias_value":"FAYME62XG52LVCGA","created_at":"2026-07-05T04:26:54Z"},{"alias_kind":"pith_short_8","alias_value":"FAYME62X","created_at":"2026-07-05T04:26:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FAYME62XG52LVCGAIPFFOVWUI7","target":"record","payload":{"canonical_record":{"source":{"id":"2205.13950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T12:49:33Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"370d0e73269487c169ab480ca0176d87e7f5362ec18f44fa21a8c0125a97644f","abstract_canon_sha256":"645a251a042d3e0982798998dfaf5405b863f30d2dc526d5f759b9524c199c74"},"schema_version":"1.0"},"canonical_sha256":"2830c27b573774ba88c043ca5756d447ce248028445e57539abf1bad1c2ae955","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:54.057740Z","signature_b64":"V/Dh/z3IU0Kt6IlZF2o0krMSEzPH6j6LO5rXdbxC4a3Kt2lKCSgPc1wpoc4D42EcdFa2upxYz3lgPeLHn/xICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2830c27b573774ba88c043ca5756d447ce248028445e57539abf1bad1c2ae955","last_reissued_at":"2026-07-05T04:26:54.057305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:54.057305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.13950","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":"2026-07-05T04:26:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QWVzuW1OIjL9GrFFtHsPXxL2IUTf+ofQHpPEFTWWn8H24bZTQTR0SQL9SdJwh1r/K9+ZvlRgnR15q174nKXcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:46:18.549167Z"},"content_sha256":"f53bcbe1de2dff7e260f8bed9c87bd4832387122be5c983a61b98ae640e52175","schema_version":"1.0","event_id":"sha256:f53bcbe1de2dff7e260f8bed9c87bd4832387122be5c983a61b98ae640e52175"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FAYME62XG52LVCGAIPFFOVWUI7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Non-Markovian policies occupancy measures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Jacob Buckman, Remi Tachet des Combes, Romain Laroche","submitted_at":"2022-05-27T12:49:33Z","abstract_excerpt":"A central object of study in Reinforcement Learning (RL) is the Markovian policy, in which an agent's actions are chosen from a memoryless probability distribution, conditioned only on its current state. The family of Markovian policies is broad enough to be interesting, yet simple enough to be amenable to analysis. However, RL often involves more complex policies: ensembles of policies, policies over options, policies updated online, etc. Our main contribution is to prove that the occupancy measure of any non-Markovian policy, i.e., the distribution of transition samples collected with it, ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13950","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.13950/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":"2026-07-05T04:26:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KKHVWbtnphRgan+ZLpGtW/n9vkNPLC5mwLKwCzZbFd+XANq90TuD5PZC4u2E3JYgqp3CK1XvbBj5DYFuu18hDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:46:18.549562Z"},"content_sha256":"f2a25110ab1ea812ed4a3f7b1db025a984da88cb5dc0fe5c8d3991fe8a724c12","schema_version":"1.0","event_id":"sha256:f2a25110ab1ea812ed4a3f7b1db025a984da88cb5dc0fe5c8d3991fe8a724c12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FAYME62XG52LVCGAIPFFOVWUI7/bundle.json","state_url":"https://pith.science/pith/FAYME62XG52LVCGAIPFFOVWUI7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FAYME62XG52LVCGAIPFFOVWUI7/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":"2026-07-09T01:46:18Z","links":{"resolver":"https://pith.science/pith/FAYME62XG52LVCGAIPFFOVWUI7","bundle":"https://pith.science/pith/FAYME62XG52LVCGAIPFFOVWUI7/bundle.json","state":"https://pith.science/pith/FAYME62XG52LVCGAIPFFOVWUI7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FAYME62XG52LVCGAIPFFOVWUI7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FAYME62XG52LVCGAIPFFOVWUI7","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":"645a251a042d3e0982798998dfaf5405b863f30d2dc526d5f759b9524c199c74","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T12:49:33Z","title_canon_sha256":"370d0e73269487c169ab480ca0176d87e7f5362ec18f44fa21a8c0125a97644f"},"schema_version":"1.0","source":{"id":"2205.13950","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13950","created_at":"2026-07-05T04:26:54Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13950v1","created_at":"2026-07-05T04:26:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13950","created_at":"2026-07-05T04:26:54Z"},{"alias_kind":"pith_short_12","alias_value":"FAYME62XG52L","created_at":"2026-07-05T04:26:54Z"},{"alias_kind":"pith_short_16","alias_value":"FAYME62XG52LVCGA","created_at":"2026-07-05T04:26:54Z"},{"alias_kind":"pith_short_8","alias_value":"FAYME62X","created_at":"2026-07-05T04:26:54Z"}],"graph_snapshots":[{"event_id":"sha256:f2a25110ab1ea812ed4a3f7b1db025a984da88cb5dc0fe5c8d3991fe8a724c12","target":"graph","created_at":"2026-07-05T04:26:54Z","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/2205.13950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A central object of study in Reinforcement Learning (RL) is the Markovian policy, in which an agent's actions are chosen from a memoryless probability distribution, conditioned only on its current state. The family of Markovian policies is broad enough to be interesting, yet simple enough to be amenable to analysis. However, RL often involves more complex policies: ensembles of policies, policies over options, policies updated online, etc. Our main contribution is to prove that the occupancy measure of any non-Markovian policy, i.e., the distribution of transition samples collected with it, ca","authors_text":"Jacob Buckman, Remi Tachet des Combes, Romain Laroche","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T12:49:33Z","title":"Non-Markovian policies occupancy measures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13950","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:f53bcbe1de2dff7e260f8bed9c87bd4832387122be5c983a61b98ae640e52175","target":"record","created_at":"2026-07-05T04:26:54Z","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":"645a251a042d3e0982798998dfaf5405b863f30d2dc526d5f759b9524c199c74","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T12:49:33Z","title_canon_sha256":"370d0e73269487c169ab480ca0176d87e7f5362ec18f44fa21a8c0125a97644f"},"schema_version":"1.0","source":{"id":"2205.13950","kind":"arxiv","version":1}},"canonical_sha256":"2830c27b573774ba88c043ca5756d447ce248028445e57539abf1bad1c2ae955","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2830c27b573774ba88c043ca5756d447ce248028445e57539abf1bad1c2ae955","first_computed_at":"2026-07-05T04:26:54.057305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:54.057305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V/Dh/z3IU0Kt6IlZF2o0krMSEzPH6j6LO5rXdbxC4a3Kt2lKCSgPc1wpoc4D42EcdFa2upxYz3lgPeLHn/xICw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:54.057740Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.13950","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f53bcbe1de2dff7e260f8bed9c87bd4832387122be5c983a61b98ae640e52175","sha256:f2a25110ab1ea812ed4a3f7b1db025a984da88cb5dc0fe5c8d3991fe8a724c12"],"state_sha256":"bc3152445c7b2aef0c91a8afa68bb7aaec608147a07c2583d1cc333f696ed14c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CbnkCh3j9loYI5ytbOyLsUhy96/ANUe9/s485HzgokFof4o6WPc+uvj2TXsBo2WujI7BQtZhmfQjw7PH3LWHDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T01:46:18.551797Z","bundle_sha256":"5cdecb7cb583acc0f5af7e0c094b2b9c10f2aa939e76b65931a767af2b114420"}}