{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:G7YAM22NQP2TGCQ3ZNTCWSHLRK","short_pith_number":"pith:G7YAM22N","canonical_record":{"source":{"id":"1904.11455","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-25T16:54:02Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"52d4e8815f5ce59f1e6f7614c18233052363d02b154ed3f68100a1114c6025d2","abstract_canon_sha256":"4377158266573881816c8428faa75b3f3c296710788e971c7b02b63e3f887226"},"schema_version":"1.0"},"canonical_sha256":"37f0066b4d83f5330a1bcb662b48eb8ab518c01e0dbe2a6047dabce42e4a053f","source":{"kind":"arxiv","id":"1904.11455","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.11455","created_at":"2026-05-17T23:47:44Z"},{"alias_kind":"arxiv_version","alias_value":"1904.11455v1","created_at":"2026-05-17T23:47:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11455","created_at":"2026-05-17T23:47:44Z"},{"alias_kind":"pith_short_12","alias_value":"G7YAM22NQP2T","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"G7YAM22NQP2TGCQ3","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"G7YAM22N","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:G7YAM22NQP2TGCQ3ZNTCWSHLRK","target":"record","payload":{"canonical_record":{"source":{"id":"1904.11455","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-25T16:54:02Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"52d4e8815f5ce59f1e6f7614c18233052363d02b154ed3f68100a1114c6025d2","abstract_canon_sha256":"4377158266573881816c8428faa75b3f3c296710788e971c7b02b63e3f887226"},"schema_version":"1.0"},"canonical_sha256":"37f0066b4d83f5330a1bcb662b48eb8ab518c01e0dbe2a6047dabce42e4a053f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:44.818536Z","signature_b64":"LNN6+GY9Mi6+wchnmeIOiEh1UvVCZqKoPQQQIJ7iTqfh01CQ1qE3YRhujT7VH+t/7caMzh6ddnmmWdlbvE2xDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37f0066b4d83f5330a1bcb662b48eb8ab518c01e0dbe2a6047dabce42e4a053f","last_reissued_at":"2026-05-17T23:47:44.817956Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:44.817956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.11455","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7R9uWD+TZWskh+BUlXDe3BN0pJIn66vRCJUn5zDsLCYSDc2mNrrQt3zD9QEkSHN50agar5TBlHZMdPn4cPf3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:09:47.926698Z"},"content_sha256":"f8ae909172ee5d9e81d94ea718ee561db2cfaaca9335a76dfb84cde0e5126851","schema_version":"1.0","event_id":"sha256:f8ae909172ee5d9e81d94ea718ee561db2cfaaca9335a76dfb84cde0e5126851"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:G7YAM22NQP2TGCQ3ZNTCWSHLRK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ray Interference: a Source of Plateaus in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Diana Borsa, Joseph Modayil, Razvan Pascanu, Tom Schaul","submitted_at":"2019-04-25T16:54:02Z","abstract_excerpt":"Rather than proposing a new method, this paper investigates an issue present in existing learning algorithms. We study the learning dynamics of reinforcement learning (RL), specifically a characteristic coupling between learning and data generation that arises because RL agents control their future data distribution. In the presence of function approximation, this coupling can lead to a problematic type of 'ray interference', characterized by learning dynamics that sequentially traverse a number of performance plateaus, effectively constraining the agent to learn one thing at a time even when "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11455","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H6f5zr4EgXrr5zlKgmiFwiMKX5OImg1sSvq9DaFd91G92Eg5iClnqTFkiiwi1YeFsGH6ernXo4ieODqJPoT5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:09:47.927384Z"},"content_sha256":"8ccf7d80f93fd643839f46d959553ba5f0f1f58ace4abf443cff9724f9606135","schema_version":"1.0","event_id":"sha256:8ccf7d80f93fd643839f46d959553ba5f0f1f58ace4abf443cff9724f9606135"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G7YAM22NQP2TGCQ3ZNTCWSHLRK/bundle.json","state_url":"https://pith.science/pith/G7YAM22NQP2TGCQ3ZNTCWSHLRK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G7YAM22NQP2TGCQ3ZNTCWSHLRK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T14:09:47Z","links":{"resolver":"https://pith.science/pith/G7YAM22NQP2TGCQ3ZNTCWSHLRK","bundle":"https://pith.science/pith/G7YAM22NQP2TGCQ3ZNTCWSHLRK/bundle.json","state":"https://pith.science/pith/G7YAM22NQP2TGCQ3ZNTCWSHLRK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G7YAM22NQP2TGCQ3ZNTCWSHLRK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:G7YAM22NQP2TGCQ3ZNTCWSHLRK","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":"4377158266573881816c8428faa75b3f3c296710788e971c7b02b63e3f887226","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-25T16:54:02Z","title_canon_sha256":"52d4e8815f5ce59f1e6f7614c18233052363d02b154ed3f68100a1114c6025d2"},"schema_version":"1.0","source":{"id":"1904.11455","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.11455","created_at":"2026-05-17T23:47:44Z"},{"alias_kind":"arxiv_version","alias_value":"1904.11455v1","created_at":"2026-05-17T23:47:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11455","created_at":"2026-05-17T23:47:44Z"},{"alias_kind":"pith_short_12","alias_value":"G7YAM22NQP2T","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"G7YAM22NQP2TGCQ3","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"G7YAM22N","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:8ccf7d80f93fd643839f46d959553ba5f0f1f58ace4abf443cff9724f9606135","target":"graph","created_at":"2026-05-17T23:47:44Z","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"},"paper":{"abstract_excerpt":"Rather than proposing a new method, this paper investigates an issue present in existing learning algorithms. We study the learning dynamics of reinforcement learning (RL), specifically a characteristic coupling between learning and data generation that arises because RL agents control their future data distribution. In the presence of function approximation, this coupling can lead to a problematic type of 'ray interference', characterized by learning dynamics that sequentially traverse a number of performance plateaus, effectively constraining the agent to learn one thing at a time even when ","authors_text":"Diana Borsa, Joseph Modayil, Razvan Pascanu, Tom Schaul","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-25T16:54:02Z","title":"Ray Interference: a Source of Plateaus in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11455","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:f8ae909172ee5d9e81d94ea718ee561db2cfaaca9335a76dfb84cde0e5126851","target":"record","created_at":"2026-05-17T23:47:44Z","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":"4377158266573881816c8428faa75b3f3c296710788e971c7b02b63e3f887226","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-25T16:54:02Z","title_canon_sha256":"52d4e8815f5ce59f1e6f7614c18233052363d02b154ed3f68100a1114c6025d2"},"schema_version":"1.0","source":{"id":"1904.11455","kind":"arxiv","version":1}},"canonical_sha256":"37f0066b4d83f5330a1bcb662b48eb8ab518c01e0dbe2a6047dabce42e4a053f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37f0066b4d83f5330a1bcb662b48eb8ab518c01e0dbe2a6047dabce42e4a053f","first_computed_at":"2026-05-17T23:47:44.817956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:44.817956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LNN6+GY9Mi6+wchnmeIOiEh1UvVCZqKoPQQQIJ7iTqfh01CQ1qE3YRhujT7VH+t/7caMzh6ddnmmWdlbvE2xDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:44.818536Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.11455","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8ae909172ee5d9e81d94ea718ee561db2cfaaca9335a76dfb84cde0e5126851","sha256:8ccf7d80f93fd643839f46d959553ba5f0f1f58ace4abf443cff9724f9606135"],"state_sha256":"e82c6c7cf5ad5525939fbca7e27c8b0eae01ebfbc04f04c06fcce64c9da8179a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I3bURN7Oui4ZHVvHbhRN+yD5/uBZlfhLZn13B0SxVFP1tOvvjcNl5zVfXB9x3fM5CDLObAWaumLsja7f4xfcCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T14:09:47.930745Z","bundle_sha256":"b0ff3d9c92c383eed11caa29816ff0f36d0a4f6044cd0e646e9471a775272d49"}}