{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HD4G5ZCBJR2BNXP6L4J77ORUXY","short_pith_number":"pith:HD4G5ZCB","schema_version":"1.0","canonical_sha256":"38f86ee4414c7416ddfe5f13ffba34be30d95bf705047d5deff7dfc36f2eddd6","source":{"kind":"arxiv","id":"2106.04379","version":4},"attestation_state":"computed","paper":{"title":"Learning Markov State Abstractions for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cameron Allen, George Konidaris, Neev Parikh, Omer Gottesman","submitted_at":"2021-06-08T14:12:36Z","abstract_excerpt":"A fundamental assumption of reinforcement learning in Markov decision processes (MDPs) is that the relevant decision process is, in fact, Markov. However, when MDPs have rich observations, agents typically learn by way of an abstract state representation, and such representations are not guaranteed to preserve the Markov property. We introduce a novel set of conditions and prove that they are sufficient for learning a Markov abstract state representation. We then describe a practical training procedure that combines inverse model estimation and temporal contrastive learning to learn an abstrac"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.04379","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T14:12:36Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2dfc803949cb0b0c0cbe7d745a377cf9a25e9db7eb23c3e2f0d22be8c6fe739d","abstract_canon_sha256":"682371fbe8ddc8b7a23005d4197bc78405fa46b40176cb20066dbbe109b1594a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:12.973124Z","signature_b64":"m1N7VoFU2d00bPAR3qASprEi0YN3Cy2xvxLm87rLmFYEJA+9ZREx/+0YG7yyurfOMz5pBOxsXkgHG1lc136sAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38f86ee4414c7416ddfe5f13ffba34be30d95bf705047d5deff7dfc36f2eddd6","last_reissued_at":"2026-07-05T07:56:12.972670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:12.972670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Markov State Abstractions for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cameron Allen, George Konidaris, Neev Parikh, Omer Gottesman","submitted_at":"2021-06-08T14:12:36Z","abstract_excerpt":"A fundamental assumption of reinforcement learning in Markov decision processes (MDPs) is that the relevant decision process is, in fact, Markov. However, when MDPs have rich observations, agents typically learn by way of an abstract state representation, and such representations are not guaranteed to preserve the Markov property. We introduce a novel set of conditions and prove that they are sufficient for learning a Markov abstract state representation. We then describe a practical training procedure that combines inverse model estimation and temporal contrastive learning to learn an abstrac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04379","kind":"arxiv","version":4},"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/2106.04379/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.04379","created_at":"2026-07-05T07:56:12.972730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.04379v4","created_at":"2026-07-05T07:56:12.972730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04379","created_at":"2026-07-05T07:56:12.972730+00:00"},{"alias_kind":"pith_short_12","alias_value":"HD4G5ZCBJR2B","created_at":"2026-07-05T07:56:12.972730+00:00"},{"alias_kind":"pith_short_16","alias_value":"HD4G5ZCBJR2BNXP6","created_at":"2026-07-05T07:56:12.972730+00:00"},{"alias_kind":"pith_short_8","alias_value":"HD4G5ZCB","created_at":"2026-07-05T07:56:12.972730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HD4G5ZCBJR2BNXP6L4J77ORUXY","json":"https://pith.science/pith/HD4G5ZCBJR2BNXP6L4J77ORUXY.json","graph_json":"https://pith.science/api/pith-number/HD4G5ZCBJR2BNXP6L4J77ORUXY/graph.json","events_json":"https://pith.science/api/pith-number/HD4G5ZCBJR2BNXP6L4J77ORUXY/events.json","paper":"https://pith.science/paper/HD4G5ZCB"},"agent_actions":{"view_html":"https://pith.science/pith/HD4G5ZCBJR2BNXP6L4J77ORUXY","download_json":"https://pith.science/pith/HD4G5ZCBJR2BNXP6L4J77ORUXY.json","view_paper":"https://pith.science/paper/HD4G5ZCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.04379&json=true","fetch_graph":"https://pith.science/api/pith-number/HD4G5ZCBJR2BNXP6L4J77ORUXY/graph.json","fetch_events":"https://pith.science/api/pith-number/HD4G5ZCBJR2BNXP6L4J77ORUXY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HD4G5ZCBJR2BNXP6L4J77ORUXY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HD4G5ZCBJR2BNXP6L4J77ORUXY/action/storage_attestation","attest_author":"https://pith.science/pith/HD4G5ZCBJR2BNXP6L4J77ORUXY/action/author_attestation","sign_citation":"https://pith.science/pith/HD4G5ZCBJR2BNXP6L4J77ORUXY/action/citation_signature","submit_replication":"https://pith.science/pith/HD4G5ZCBJR2BNXP6L4J77ORUXY/action/replication_record"}},"created_at":"2026-07-05T07:56:12.972730+00:00","updated_at":"2026-07-05T07:56:12.972730+00:00"}