{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:252V4KC6BTB4IMVYOAJK5BJ22N","short_pith_number":"pith:252V4KC6","canonical_record":{"source":{"id":"2009.04777","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T11:23:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7f1e3b412f305b97b441816df34387ccd2cee5ce548759f7672b3c70ca75a981","abstract_canon_sha256":"e886237d3dcc57e95ded512606e852583d71efa21a3049a919e2ef68b76d8619"},"schema_version":"1.0"},"canonical_sha256":"d7755e285e0cc3c432b87012ae853ad3616112f8a079be138ed7cd10c9e98745","source":{"kind":"arxiv","id":"2009.04777","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.04777","created_at":"2026-07-05T01:34:29Z"},{"alias_kind":"arxiv_version","alias_value":"2009.04777v1","created_at":"2026-07-05T01:34:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.04777","created_at":"2026-07-05T01:34:29Z"},{"alias_kind":"pith_short_12","alias_value":"252V4KC6BTB4","created_at":"2026-07-05T01:34:29Z"},{"alias_kind":"pith_short_16","alias_value":"252V4KC6BTB4IMVY","created_at":"2026-07-05T01:34:29Z"},{"alias_kind":"pith_short_8","alias_value":"252V4KC6","created_at":"2026-07-05T01:34:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:252V4KC6BTB4IMVYOAJK5BJ22N","target":"record","payload":{"canonical_record":{"source":{"id":"2009.04777","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T11:23:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7f1e3b412f305b97b441816df34387ccd2cee5ce548759f7672b3c70ca75a981","abstract_canon_sha256":"e886237d3dcc57e95ded512606e852583d71efa21a3049a919e2ef68b76d8619"},"schema_version":"1.0"},"canonical_sha256":"d7755e285e0cc3c432b87012ae853ad3616112f8a079be138ed7cd10c9e98745","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:29.646046Z","signature_b64":"au8EBpTRy36j43EXw72oiU0vIps43N8QMZQwS0/DOYJEZFnaCdMx4weExX74f2ysXy7YX5bgRkaRJyTRW/fEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7755e285e0cc3c432b87012ae853ad3616112f8a079be138ed7cd10c9e98745","last_reissued_at":"2026-07-05T01:34:29.645646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:29.645646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.04777","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":"2026-07-05T01:34:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7iHgaCdd2IdXakSlWx5ZYmMRe5DtuBhLLwuC9vy8szbzzTAVoRdr2QYY7fjr9GhV5z/eg3k6NHKqt0lQ28cFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:52:23.876277Z"},"content_sha256":"402c02b68cedc0696f0e4105e7f9137454524b8160dbfee3d2d279e77431542e","schema_version":"1.0","event_id":"sha256:402c02b68cedc0696f0e4105e7f9137454524b8160dbfee3d2d279e77431542e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:252V4KC6BTB4IMVYOAJK5BJ22N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A framework for reinforcement learning with autocorrelated actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jakub {\\L}yskawa, Marcin Szulc, Pawe{\\l} Wawrzy\\'nski","submitted_at":"2020-09-10T11:23:09Z","abstract_excerpt":"The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are distributed over time and potentially give better clues to policy improvement. Also, physical implementation of such policies, e.g. in robotics, is less problematic, as it avoids making robots shake. This is in opposition to most RL algorithms which add white noise to control causing unwanted shaking of the robots. An algorithm is introduced here that approxi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.04777","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/2009.04777/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":"2026-07-05T01:34:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oB12ygBhvKSI+F0EJss4usDPwEkKesdbbMrwlRv56S234Dp9f+m5WkWdWJH8CAeHAZ5DVB299cw1/V7ik3mzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:52:23.876771Z"},"content_sha256":"30d0dbd542f49ad9d95a74aa86ce1721efca9c468c06fa8da1bfd7a3107fb82d","schema_version":"1.0","event_id":"sha256:30d0dbd542f49ad9d95a74aa86ce1721efca9c468c06fa8da1bfd7a3107fb82d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/252V4KC6BTB4IMVYOAJK5BJ22N/bundle.json","state_url":"https://pith.science/pith/252V4KC6BTB4IMVYOAJK5BJ22N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/252V4KC6BTB4IMVYOAJK5BJ22N/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":"2026-08-06T07:52:23Z","links":{"resolver":"https://pith.science/pith/252V4KC6BTB4IMVYOAJK5BJ22N","bundle":"https://pith.science/pith/252V4KC6BTB4IMVYOAJK5BJ22N/bundle.json","state":"https://pith.science/pith/252V4KC6BTB4IMVYOAJK5BJ22N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/252V4KC6BTB4IMVYOAJK5BJ22N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:252V4KC6BTB4IMVYOAJK5BJ22N","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":"e886237d3dcc57e95ded512606e852583d71efa21a3049a919e2ef68b76d8619","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T11:23:09Z","title_canon_sha256":"7f1e3b412f305b97b441816df34387ccd2cee5ce548759f7672b3c70ca75a981"},"schema_version":"1.0","source":{"id":"2009.04777","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.04777","created_at":"2026-07-05T01:34:29Z"},{"alias_kind":"arxiv_version","alias_value":"2009.04777v1","created_at":"2026-07-05T01:34:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.04777","created_at":"2026-07-05T01:34:29Z"},{"alias_kind":"pith_short_12","alias_value":"252V4KC6BTB4","created_at":"2026-07-05T01:34:29Z"},{"alias_kind":"pith_short_16","alias_value":"252V4KC6BTB4IMVY","created_at":"2026-07-05T01:34:29Z"},{"alias_kind":"pith_short_8","alias_value":"252V4KC6","created_at":"2026-07-05T01:34:29Z"}],"graph_snapshots":[{"event_id":"sha256:30d0dbd542f49ad9d95a74aa86ce1721efca9c468c06fa8da1bfd7a3107fb82d","target":"graph","created_at":"2026-07-05T01:34:29Z","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/2009.04777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are distributed over time and potentially give better clues to policy improvement. Also, physical implementation of such policies, e.g. in robotics, is less problematic, as it avoids making robots shake. This is in opposition to most RL algorithms which add white noise to control causing unwanted shaking of the robots. An algorithm is introduced here that approxi","authors_text":"Jakub {\\L}yskawa, Marcin Szulc, Pawe{\\l} Wawrzy\\'nski","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T11:23:09Z","title":"A framework for reinforcement learning with autocorrelated actions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.04777","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":"sha256:402c02b68cedc0696f0e4105e7f9137454524b8160dbfee3d2d279e77431542e","target":"record","created_at":"2026-07-05T01:34:29Z","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":"e886237d3dcc57e95ded512606e852583d71efa21a3049a919e2ef68b76d8619","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T11:23:09Z","title_canon_sha256":"7f1e3b412f305b97b441816df34387ccd2cee5ce548759f7672b3c70ca75a981"},"schema_version":"1.0","source":{"id":"2009.04777","kind":"arxiv","version":1}},"canonical_sha256":"d7755e285e0cc3c432b87012ae853ad3616112f8a079be138ed7cd10c9e98745","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7755e285e0cc3c432b87012ae853ad3616112f8a079be138ed7cd10c9e98745","first_computed_at":"2026-07-05T01:34:29.645646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:34:29.645646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"au8EBpTRy36j43EXw72oiU0vIps43N8QMZQwS0/DOYJEZFnaCdMx4weExX74f2ysXy7YX5bgRkaRJyTRW/fEAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:34:29.646046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.04777","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:402c02b68cedc0696f0e4105e7f9137454524b8160dbfee3d2d279e77431542e","sha256:30d0dbd542f49ad9d95a74aa86ce1721efca9c468c06fa8da1bfd7a3107fb82d"],"state_sha256":"21cffa43d645198f4d55690fbbc6ad0ef17e689a5158b68dd11b5d47f353ae3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ejt8nvhMRLjM2OKra7bUpBjjqDlzXtO90gKdhm3QpItqnEKGGaw5AoGZNIdvp0Mzvi2/XWbdk0Sp6xgisMfVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:52:23.880124Z","bundle_sha256":"dac930e2d89489678c24be7da0dd04dbcd3a3d65b3e3431f37d17049f062a093"}}