{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G3SY5TXN6ZZGWSCHG6WKQCC7J7","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":"095bc5b2614f9357ef5d4fe317f0ca4140b6725637e8af51470738d63e094f28","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T19:37:43Z","title_canon_sha256":"77d4d1ffb9e88274ffa60c1bde0b4b47884ce60fc6bd5cd579e8ccf46f73f476"},"schema_version":"1.0","source":{"id":"2306.09466","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09466","created_at":"2026-07-05T06:21:20Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09466v1","created_at":"2026-07-05T06:21:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09466","created_at":"2026-07-05T06:21:20Z"},{"alias_kind":"pith_short_12","alias_value":"G3SY5TXN6ZZG","created_at":"2026-07-05T06:21:20Z"},{"alias_kind":"pith_short_16","alias_value":"G3SY5TXN6ZZGWSCH","created_at":"2026-07-05T06:21:20Z"},{"alias_kind":"pith_short_8","alias_value":"G3SY5TXN","created_at":"2026-07-05T06:21:20Z"}],"graph_snapshots":[{"event_id":"sha256:abbf2769b0a04c56d7ad06ecd1affeae098191fb1d6b0d4e597fda7fe6b30d51","target":"graph","created_at":"2026-07-05T06:21:20Z","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/2306.09466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficiency, recent work focuses on model-based RL which interleaves model learning with planning. Recent methods further utilize policy learning, value estimation, and, self-supervised learning as auxiliary objectives. In this paper we show that, surprisingly, a simple representation learning approach relying only on a latent dynamics model trained by latent temporal consistency is sufficient for high-performance RL. This app","authors_text":"Joni Pajarinen, Juho Kannala, Rinu Boney, Wenshuai Zhao, Yi Zhao","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T19:37:43Z","title":"Simplified Temporal Consistency Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09466","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":"sha256:7276ba2145c9aea7b6e2bdecc08b14b44aaaf66e80169abf36b1a35aed0a0c56","target":"record","created_at":"2026-07-05T06:21:20Z","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":"095bc5b2614f9357ef5d4fe317f0ca4140b6725637e8af51470738d63e094f28","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T19:37:43Z","title_canon_sha256":"77d4d1ffb9e88274ffa60c1bde0b4b47884ce60fc6bd5cd579e8ccf46f73f476"},"schema_version":"1.0","source":{"id":"2306.09466","kind":"arxiv","version":1}},"canonical_sha256":"36e58eceedf6726b484737aca8085f4ffec480dc7ed37921a8e1a6f6eac28519","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36e58eceedf6726b484737aca8085f4ffec480dc7ed37921a8e1a6f6eac28519","first_computed_at":"2026-07-05T06:21:20.301662Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:20.301662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UqpKwaGfeuhxaAtpzq2su+oHeYjc4Fj2XeA+X4q/Pr6GuFH2Bj+UBHKmxlCUoxtHqU6cUyS3kM67SpvLzSzJDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:20.302129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09466","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7276ba2145c9aea7b6e2bdecc08b14b44aaaf66e80169abf36b1a35aed0a0c56","sha256:abbf2769b0a04c56d7ad06ecd1affeae098191fb1d6b0d4e597fda7fe6b30d51"],"state_sha256":"a611d54ab5f8fc397eb07926f311b71d1ef0c0daf684d98b539949d4421683c1"}