{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SLZYKEXFCSPECCYF3LFCJSSOQO","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":"a0fe3bdabd3b3fbc1ee25af15f35d7fedc68265db7f0f6d7cd1924158566bf36","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-10T07:05:27Z","title_canon_sha256":"416c37cb5ce16a1cc3db4a4f088ef169ec14d001e376b64f03d795d32f23c936"},"schema_version":"1.0","source":{"id":"1905.03970","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.03970","created_at":"2026-07-05T01:08:09Z"},{"alias_kind":"arxiv_version","alias_value":"1905.03970v4","created_at":"2026-07-05T01:08:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03970","created_at":"2026-07-05T01:08:09Z"},{"alias_kind":"pith_short_12","alias_value":"SLZYKEXFCSPE","created_at":"2026-07-05T01:08:09Z"},{"alias_kind":"pith_short_16","alias_value":"SLZYKEXFCSPECCYF","created_at":"2026-07-05T01:08:09Z"},{"alias_kind":"pith_short_8","alias_value":"SLZYKEXF","created_at":"2026-07-05T01:08:09Z"}],"graph_snapshots":[{"event_id":"sha256:8948706480f41a6f086fc0460da11bc2926c7a59bb742e3476c090e68262114e","target":"graph","created_at":"2026-07-05T01:08:09Z","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/1905.03970/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) methods learn optimal decisions in the presence of a stationary environment. However, the stationary assumption on the environment is very restrictive. In many real world problems like traffic signal control, robotic applications, one often encounters situations with non-stationary environments and in these scenarios, RL methods yield sub-optimal decisions. In this paper, we thus consider the problem of developing RL methods that obtain optimal decisions in a non-stationary environment. The goal of this problem is to maximize the long-term discounted reward achieved","authors_text":"Prabuchandran K. J, Shalabh Bhatnagar, Sindhu Padakandla","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-10T07:05:27Z","title":"Reinforcement Learning in Non-Stationary Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03970","kind":"arxiv","version":4},"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:a06b88b8f13fecdd27d3f00440597d1a46becfcd0e065a5bab39b206088aa6a0","target":"record","created_at":"2026-07-05T01:08:09Z","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":"a0fe3bdabd3b3fbc1ee25af15f35d7fedc68265db7f0f6d7cd1924158566bf36","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-10T07:05:27Z","title_canon_sha256":"416c37cb5ce16a1cc3db4a4f088ef169ec14d001e376b64f03d795d32f23c936"},"schema_version":"1.0","source":{"id":"1905.03970","kind":"arxiv","version":4}},"canonical_sha256":"92f38512e5149e410b05daca24ca4e83bf94f6a6e067c5b3f61f46c8ea1b64d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92f38512e5149e410b05daca24ca4e83bf94f6a6e067c5b3f61f46c8ea1b64d9","first_computed_at":"2026-07-05T01:08:09.522285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:08:09.522285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mIr1EENfDmEpQiEHv903qiFjyfmiOvX5BQcQVZQqIDJBZLyuq1wb2nIVCHwOfssBt+8kxfhkNpuUv34GDes/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:08:09.522781Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.03970","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a06b88b8f13fecdd27d3f00440597d1a46becfcd0e065a5bab39b206088aa6a0","sha256:8948706480f41a6f086fc0460da11bc2926c7a59bb742e3476c090e68262114e"],"state_sha256":"f23d9fd51ecde6a734163646a1df453043e42738decaf80b1384a238497090b6"}