{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GWL3RHIK5ME3BNW6V27EYUWG4R","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":"3389f1adc3e085c8e5d819567a462b712c870aa9bbab9b6321b483f373603340","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-12T07:38:15Z","title_canon_sha256":"40597aff44788720a975f74c6cacf3a2877de9efd2814f04b5901fd4e0265d78"},"schema_version":"1.0","source":{"id":"2007.05929","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.05929","created_at":"2026-07-05T02:41:47Z"},{"alias_kind":"arxiv_version","alias_value":"2007.05929v4","created_at":"2026-07-05T02:41:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.05929","created_at":"2026-07-05T02:41:47Z"},{"alias_kind":"pith_short_12","alias_value":"GWL3RHIK5ME3","created_at":"2026-07-05T02:41:47Z"},{"alias_kind":"pith_short_16","alias_value":"GWL3RHIK5ME3BNW6","created_at":"2026-07-05T02:41:47Z"},{"alias_kind":"pith_short_8","alias_value":"GWL3RHIK","created_at":"2026-07-05T02:41:47Z"}],"graph_snapshots":[{"event_id":"sha256:bafbdc32029bd775a67bf106f004d9732e8477390d139fca164177a748d1e866","target":"graph","created_at":"2026-07-05T02:41:47Z","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/2007.05929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While deep reinforcement learning excels at solving tasks where large amounts of data can be collected through virtually unlimited interaction with the environment, learning from limited interaction remains a key challenge. We posit that an agent can learn more efficiently if we augment reward maximization with self-supervised objectives based on structure in its visual input and sequential interaction with the environment. Our method, Self-Predictive Representations(SPR), trains an agent to predict its own latent state representations multiple steps into the future. We compute target represen","authors_text":"Aaron Courville, Ankesh Anand, Max Schwarzer, Philip Bachman, R Devon Hjelm, Rishab Goel","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-12T07:38:15Z","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.05929","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:a748cb0b1fde8ae51ed64b2571c706a41c39ae9a4c6d9fd2b4ebb57f3b083ccf","target":"record","created_at":"2026-07-05T02:41:47Z","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":"3389f1adc3e085c8e5d819567a462b712c870aa9bbab9b6321b483f373603340","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-12T07:38:15Z","title_canon_sha256":"40597aff44788720a975f74c6cacf3a2877de9efd2814f04b5901fd4e0265d78"},"schema_version":"1.0","source":{"id":"2007.05929","kind":"arxiv","version":4}},"canonical_sha256":"3597b89d0aeb09b0b6deaebe4c52c6e449e93bf848d855fde2bd971e099fdb79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3597b89d0aeb09b0b6deaebe4c52c6e449e93bf848d855fde2bd971e099fdb79","first_computed_at":"2026-07-05T02:41:47.427829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:41:47.427829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A0304cdQpVOVJePB5oDJyjGGQ8WF5B6hglfzh86LUF75IsT3trIS/NyNoASiamwTmwsSyTkEy1exU3uYFL06Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:41:47.428352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.05929","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a748cb0b1fde8ae51ed64b2571c706a41c39ae9a4c6d9fd2b4ebb57f3b083ccf","sha256:bafbdc32029bd775a67bf106f004d9732e8477390d139fca164177a748d1e866"],"state_sha256":"486145f4d078dc6112de7b70ca669170422b1e181f08dc3ddf336a84ddb01f11"}