{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:M7IJ3EYNKX4LQOPSTMUHEZ5XF2","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":"49a9b7545214df70a346264bf05d13757cadb9b549ae89adad44439ffd63735a","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-03T08:52:40Z","title_canon_sha256":"749f4748816750180fe1ad557d3f06ed381bceb4b4adb82ebd7512d6af4f55ce"},"schema_version":"1.0","source":{"id":"2207.00986","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.00986","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2207.00986v1","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00986","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"M7IJ3EYNKX4L","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"M7IJ3EYNKX4LQOPS","created_at":"2026-07-05T04:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"M7IJ3EYN","created_at":"2026-07-05T04:36:54Z"}],"graph_snapshots":[{"event_id":"sha256:4596719c0b8de46f7f9abb3dc4e4c4443ad3dd7492274809808113f2b34799d4","target":"graph","created_at":"2026-07-05T04:36:54Z","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/2207.00986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy reinforcement learning (RL) from pixel observations is notoriously unstable. As a result, many successful algorithms must combine different domain-specific practices and auxiliary losses to learn meaningful behaviors in complex environments. In this work, we provide novel analysis demonstrating that these instabilities arise from performing temporal-difference learning with a convolutional encoder and low-magnitude rewards. We show that this new visual deadly triad causes unstable training and premature convergence to degenerate solutions, a phenomenon we name catastrophic self-over","authors_text":"Edoardo Cetin, Oya Celiktutan, Philip J. Ball, Steve Roberts","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-03T08:52:40Z","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00986","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":"sha256:09980c26895cb66bc7d57a9fbcece4f1fbb5c2cfcc8e18c6a79529e01926b8b9","target":"record","created_at":"2026-07-05T04:36:54Z","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":"49a9b7545214df70a346264bf05d13757cadb9b549ae89adad44439ffd63735a","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-03T08:52:40Z","title_canon_sha256":"749f4748816750180fe1ad557d3f06ed381bceb4b4adb82ebd7512d6af4f55ce"},"schema_version":"1.0","source":{"id":"2207.00986","kind":"arxiv","version":1}},"canonical_sha256":"67d09d930d55f8b839f29b287267b72e81fedf3978b8d060b402f6943e638e0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67d09d930d55f8b839f29b287267b72e81fedf3978b8d060b402f6943e638e0a","first_computed_at":"2026-07-05T04:36:54.806148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:54.806148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RkQEGT8rG5w/C3LNIQatLO5qO2Gn5OWI/Wn8utUO3ey/umTNciVhe0Oj7FqZPY5HauRfGwIea/M8UXHW7suXAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:54.806569Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.00986","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09980c26895cb66bc7d57a9fbcece4f1fbb5c2cfcc8e18c6a79529e01926b8b9","sha256:4596719c0b8de46f7f9abb3dc4e4c4443ad3dd7492274809808113f2b34799d4"],"state_sha256":"0d30834811540b90bd3351303ab423597da8e28294588893cb877f61032dcf00"}