{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CZ4272KVMEHHG4SSMSEYVDT4HG","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":"090baa7d3b6aaa5d50d71402374fd70a549f2a3a0cabb338334adb48c7076e98","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-14T08:52:36Z","title_canon_sha256":"27228d059baa730b0dac66ced9f8ae984cc54e43db2d70902a467e5b79f9e5f6"},"schema_version":"1.0","source":{"id":"2202.06557","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.06557","created_at":"2026-07-05T03:56:39Z"},{"alias_kind":"arxiv_version","alias_value":"2202.06557v1","created_at":"2026-07-05T03:56:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06557","created_at":"2026-07-05T03:56:39Z"},{"alias_kind":"pith_short_12","alias_value":"CZ4272KVMEHH","created_at":"2026-07-05T03:56:39Z"},{"alias_kind":"pith_short_16","alias_value":"CZ4272KVMEHHG4SS","created_at":"2026-07-05T03:56:39Z"},{"alias_kind":"pith_short_8","alias_value":"CZ4272KV","created_at":"2026-07-05T03:56:39Z"}],"graph_snapshots":[{"event_id":"sha256:eeb6b7efde8aa7a2d4456545766cb2a6deb1c256c358740fc58dc3beddb414f5","target":"graph","created_at":"2026-07-05T03:56:39Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2202.06557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider a context-dependent Reinforcement Learning (RL) setting, which is characterized by: a) an unknown finite number of not directly observable contexts; b) abrupt (discontinuous) context changes occurring during an episode; and c) Markovian context evolution. We argue that this challenging case is often met in applications and we tackle it using a Bayesian approach and variational inference. We adapt a sticky Hierarchical Dirichlet Process (HDP) prior for model learning, which is arguably best-suited for Markov process modeling. We then derive a context distillation procedure, which id","authors_text":"Aivar Sootla, Haitham Bou-Ammar, Hang Ren, Jun Wang, Junxiao Shen, Taher Jafferjee","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-14T08:52:36Z","title":"Reinforcement Learning in Presence of Discrete Markovian Context Evolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06557","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":"sha256:1887c75ba4b83bfe851a3a3637c9e1d2b028ccbefee22727f16bde6ef23299e9","target":"record","created_at":"2026-07-05T03:56:39Z","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":"090baa7d3b6aaa5d50d71402374fd70a549f2a3a0cabb338334adb48c7076e98","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-14T08:52:36Z","title_canon_sha256":"27228d059baa730b0dac66ced9f8ae984cc54e43db2d70902a467e5b79f9e5f6"},"schema_version":"1.0","source":{"id":"2202.06557","kind":"arxiv","version":1}},"canonical_sha256":"1679afe955610e73725264898a8e7c399064cb5bb0b92a604be3f7ab388704f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1679afe955610e73725264898a8e7c399064cb5bb0b92a604be3f7ab388704f3","first_computed_at":"2026-07-05T03:56:39.803018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:56:39.803018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K/YOeHdaQPR4BniDNkJo7s/jFZTctJ7uZ9v7WqI7/bYGP/FBr5/VsNYCmKNapsAYnoNMgSP+sT2GRnY0liATAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:56:39.803406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.06557","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1887c75ba4b83bfe851a3a3637c9e1d2b028ccbefee22727f16bde6ef23299e9","sha256:eeb6b7efde8aa7a2d4456545766cb2a6deb1c256c358740fc58dc3beddb414f5"],"state_sha256":"daf49b30f8845bfa39af6ec90025590e377f836a7220043423495f9b79c168a4"}