{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:V4NOYPFF5FCMPFM2A3HY7D5RAV","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":"8e2e9329241f054a44509d300696c055396b00fd255045ee77dae519d36e69df","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T17:34:50Z","title_canon_sha256":"28a39f9dfe48a5af5bf6b8bdb2296e0b58ca8ac1d54c997eec3baf1d334e4a95"},"schema_version":"1.0","source":{"id":"2006.10701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.10701","created_at":"2026-07-05T01:11:20Z"},{"alias_kind":"arxiv_version","alias_value":"2006.10701v1","created_at":"2026-07-05T01:11:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10701","created_at":"2026-07-05T01:11:20Z"},{"alias_kind":"pith_short_12","alias_value":"V4NOYPFF5FCM","created_at":"2026-07-05T01:11:20Z"},{"alias_kind":"pith_short_16","alias_value":"V4NOYPFF5FCMPFM2","created_at":"2026-07-05T01:11:20Z"},{"alias_kind":"pith_short_8","alias_value":"V4NOYPFF","created_at":"2026-07-05T01:11:20Z"}],"graph_snapshots":[{"event_id":"sha256:490db2a6281cdfcd681090e7399f5ec2ddbbe719e7e8116ec6cc8296e5f1bd6f","target":"graph","created_at":"2026-07-05T01:11:20Z","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/2006.10701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As humans, our goals and our environment are persistently changing throughout our lifetime based on our experiences, actions, and internal and external drives. In contrast, typical reinforcement learning problem set-ups consider decision processes that are stationary across episodes. Can we develop reinforcement learning algorithms that can cope with the persistent change in the former, more realistic problem settings? While on-policy algorithms such as policy gradients in principle can be extended to non-stationary settings, the same cannot be said for more efficient off-policy algorithms tha","authors_text":"Annie Xie, Chelsea Finn, James Harrison","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T17:34:50Z","title":"Deep Reinforcement Learning amidst Lifelong Non-Stationarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10701","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":"sha256:8e3f6b452497d44e6377fa312b4e96fa2b308674f992a5aed63fb9c033df91f1","target":"record","created_at":"2026-07-05T01:11:20Z","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":"8e2e9329241f054a44509d300696c055396b00fd255045ee77dae519d36e69df","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T17:34:50Z","title_canon_sha256":"28a39f9dfe48a5af5bf6b8bdb2296e0b58ca8ac1d54c997eec3baf1d334e4a95"},"schema_version":"1.0","source":{"id":"2006.10701","kind":"arxiv","version":1}},"canonical_sha256":"af1aec3ca5e944c7959a06cf8f8fb1056a94a16e359027ec6d2f84a6817c411f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af1aec3ca5e944c7959a06cf8f8fb1056a94a16e359027ec6d2f84a6817c411f","first_computed_at":"2026-07-05T01:11:20.399822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:20.399822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TY7MkkL7SHI5TMOQ8X/YRKEdugAGagdqW4V2ryZW8AUVbtPURdEJTFew/3ZgMnYW41Jy9GxOaEseRyN3PuGpDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:20.400232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.10701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e3f6b452497d44e6377fa312b4e96fa2b308674f992a5aed63fb9c033df91f1","sha256:490db2a6281cdfcd681090e7399f5ec2ddbbe719e7e8116ec6cc8296e5f1bd6f"],"state_sha256":"b82f68d917fe2c8279224ad7fe6ba7fbbff8b65bb6b5eaed0cde3a923be7eebb"}