{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CHNPCYUZRL6TUNXMNEOXDU55RH","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":"5b8ca7f8093c19523d4f5e940633d11818bf7b3961ff201ccd0d7223de396f7a","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-14T19:11:13Z","title_canon_sha256":"bc134e0a594e51143b38059288491a7277e17f7dbda05a340f832b07aa8423be"},"schema_version":"1.0","source":{"id":"2009.08319","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.08319","created_at":"2026-07-05T02:40:28Z"},{"alias_kind":"arxiv_version","alias_value":"2009.08319v3","created_at":"2026-07-05T02:40:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.08319","created_at":"2026-07-05T02:40:28Z"},{"alias_kind":"pith_short_12","alias_value":"CHNPCYUZRL6T","created_at":"2026-07-05T02:40:28Z"},{"alias_kind":"pith_short_16","alias_value":"CHNPCYUZRL6TUNXM","created_at":"2026-07-05T02:40:28Z"},{"alias_kind":"pith_short_8","alias_value":"CHNPCYUZ","created_at":"2026-07-05T02:40:28Z"}],"graph_snapshots":[{"event_id":"sha256:125c444ae502f46b46fbb4e87da7870202ab279a6656017f7fe013b2bf9755ee","target":"graph","created_at":"2026-07-05T02:40:28Z","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/2009.08319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In an effort to overcome limitations of reward-driven feature learning in deep reinforcement learning (RL) from images, we propose decoupling representation learning from policy learning. To this end, we introduce a new unsupervised learning (UL) task, called Augmented Temporal Contrast (ATC), which trains a convolutional encoder to associate pairs of observations separated by a short time difference, under image augmentations and using a contrastive loss. In online RL experiments, we show that training the encoder exclusively using ATC matches or outperforms end-to-end RL in most environments","authors_text":"Adam Stooke, Kimin Lee, Michael Laskin, Pieter Abbeel","cross_cats":["cs.AI","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-14T19:11:13Z","title":"Decoupling Representation Learning from Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.08319","kind":"arxiv","version":3},"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":"sha256:8dbfce81ee487d20895f51461ac281d10964c45356d0a15d30e1108c291bd6a9","target":"record","created_at":"2026-07-05T02:40:28Z","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":"5b8ca7f8093c19523d4f5e940633d11818bf7b3961ff201ccd0d7223de396f7a","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-14T19:11:13Z","title_canon_sha256":"bc134e0a594e51143b38059288491a7277e17f7dbda05a340f832b07aa8423be"},"schema_version":"1.0","source":{"id":"2009.08319","kind":"arxiv","version":3}},"canonical_sha256":"11daf162998afd3a36ec691d71d3bd89ea8961c5038890e3b9bee0f170f979a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11daf162998afd3a36ec691d71d3bd89ea8961c5038890e3b9bee0f170f979a0","first_computed_at":"2026-07-05T02:40:28.859807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:40:28.859807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ry08yBKUOwQHB75Qdw+uKVm4XOH27pBpYU8tXLOCaL10YYZjm3WIcpq7MxxLl4IpZa1caZdksQF1a89eD0VHAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:40:28.860231Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.08319","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dbfce81ee487d20895f51461ac281d10964c45356d0a15d30e1108c291bd6a9","sha256:125c444ae502f46b46fbb4e87da7870202ab279a6656017f7fe013b2bf9755ee"],"state_sha256":"de003dc7d22d36fd6fc9334f009ff68dacb43adb79e95366b82ed0bc1c43ba21"}