{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S3HYM3XNWXQHPFAP5WJSYJPY35","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":"6c9a2c344b934c1e3f5be27dacb2cd48e2a8e1b5dd9e26b5810425479044d7de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T18:15:44Z","title_canon_sha256":"492486e545ed60997821a8be3125c18c9af04cb1fdcc03ae59d504c8fe054606"},"schema_version":"1.0","source":{"id":"2406.02696","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02696","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02696v1","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02696","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"pith_short_12","alias_value":"S3HYM3XNWXQH","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"pith_short_16","alias_value":"S3HYM3XNWXQHPFAP","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"pith_short_8","alias_value":"S3HYM3XN","created_at":"2026-07-05T08:27:29Z"}],"graph_snapshots":[{"event_id":"sha256:251fcd78405ae2190f057f45e558c5715e6b96d2a3b207b0a8c0d265bfebd7dd","target":"graph","created_at":"2026-07-05T08:27:29Z","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/2406.02696/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning representations for reinforcement learning (RL) has shown much promise for continuous control. We propose an efficient representation learning method using only a self-supervised latent-state consistency loss. Our approach employs an encoder and a dynamics model to map observations to latent states and predict future latent states, respectively. We achieve high performance and prevent representation collapse by quantizing the latent representation such that the rank of the representation is empirically preserved. Our method, named iQRL: implicitly Quantized Reinforcement Learning, is ","authors_text":"Aidan Scannell, Arno Solin, Joni Pajarinen, Kalle Kujanp\\\"a\\\"a, Mohammadreza Nakhaei, Yi Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T18:15:44Z","title":"iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02696","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:efbcc3e95090c57b92451124dadf23e08688ba67492b3cf571a0f8a08123a287","target":"record","created_at":"2026-07-05T08:27:29Z","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":"6c9a2c344b934c1e3f5be27dacb2cd48e2a8e1b5dd9e26b5810425479044d7de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T18:15:44Z","title_canon_sha256":"492486e545ed60997821a8be3125c18c9af04cb1fdcc03ae59d504c8fe054606"},"schema_version":"1.0","source":{"id":"2406.02696","kind":"arxiv","version":1}},"canonical_sha256":"96cf866eedb5e077940fed932c25f8df7ac40df3a2b766b24da0e6829d0ea8b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96cf866eedb5e077940fed932c25f8df7ac40df3a2b766b24da0e6829d0ea8b5","first_computed_at":"2026-07-05T08:27:29.033700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:29.033700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PteWsMnt6bOFuoPSWVr0/stDscThDmtixNOg828kxCdihNx0pSd2svemfFHJK3iUmNb2UuYuVwZzuwNA9kPPCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:29.034168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02696","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efbcc3e95090c57b92451124dadf23e08688ba67492b3cf571a0f8a08123a287","sha256:251fcd78405ae2190f057f45e558c5715e6b96d2a3b207b0a8c0d265bfebd7dd"],"state_sha256":"95d0cf4ecce6b0755630c4de13bae56e2facd040986b872bc419b4b6e99147fe"}