{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QQ7R6EJW24H43WBTIWMK75L4QR","short_pith_number":"pith:QQ7R6EJW","canonical_record":{"source":{"id":"2303.08631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-15T13:58:07Z","cross_cats_sorted":[],"title_canon_sha256":"067447292a53d0d4dad1eb0cd557ed82d41966b67b7ceda1d31e28a5d1eea0e2","abstract_canon_sha256":"8f36010afe02f34c913cc7d66c1f8cfb7f7254bef24e630fac76e3a7d382fd91"},"schema_version":"1.0"},"canonical_sha256":"843f1f1136d70fcdd8334598aff57c8461324295a04fc4e608c9eeb43e3721da","source":{"kind":"arxiv","id":"2303.08631","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.08631","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"arxiv_version","alias_value":"2303.08631v1","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08631","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"pith_short_12","alias_value":"QQ7R6EJW24H4","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"pith_short_16","alias_value":"QQ7R6EJW24H43WBT","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"pith_short_8","alias_value":"QQ7R6EJW","created_at":"2026-07-05T05:51:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QQ7R6EJW24H43WBTIWMK75L4QR","target":"record","payload":{"canonical_record":{"source":{"id":"2303.08631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-15T13:58:07Z","cross_cats_sorted":[],"title_canon_sha256":"067447292a53d0d4dad1eb0cd557ed82d41966b67b7ceda1d31e28a5d1eea0e2","abstract_canon_sha256":"8f36010afe02f34c913cc7d66c1f8cfb7f7254bef24e630fac76e3a7d382fd91"},"schema_version":"1.0"},"canonical_sha256":"843f1f1136d70fcdd8334598aff57c8461324295a04fc4e608c9eeb43e3721da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:35.325103Z","signature_b64":"N2KCLsd/Dbk72buCTIf2zlMiv+AW1hKcSaeNdF8mx+ODQ7aq3buDT4dbruvRHBS3s3AocVYqTHEykcnxSEVUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"843f1f1136d70fcdd8334598aff57c8461324295a04fc4e608c9eeb43e3721da","last_reissued_at":"2026-07-05T05:51:35.324681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:35.324681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.08631","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":"2026-07-05T05:51:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4c/+SlgvIIu7zXtf8vI1oWJl+XWheoh7ylNwyBVc7+BFKpZuCmX4OWmxN/FtxMKpCqWoA7z6btCPW/gb7lauBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:08:39.150616Z"},"content_sha256":"0eb926639b4b021ead2e48fb899a823f7897f7faef387ad16ef6690492f62100","schema_version":"1.0","event_id":"sha256:0eb926639b4b021ead2e48fb899a823f7897f7faef387ad16ef6690492f62100"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QQ7R6EJW24H43WBTIWMK75L4QR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Smoothed Q-learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Barber","submitted_at":"2023-03-15T13:58:07Z","abstract_excerpt":"In Reinforcement Learning the Q-learning algorithm provably converges to the optimal solution. However, as others have demonstrated, Q-learning can also overestimate the values and thereby spend too long exploring unhelpful states. Double Q-learning is a provably convergent alternative that mitigates some of the overestimation issues, though sometimes at the expense of slower convergence. We introduce an alternative algorithm that replaces the max operation with an average, resulting also in a provably convergent off-policy algorithm which can mitigate overestimation yet retain similar converg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08631","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.08631/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T05:51:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PtlJemtvUM0bTgnFm264QhN47uaszY+bc2g6auR4bglLs6V3dbnRM7ZsB7WShBCxUxkEq8uVD6KL3jDo5J+7CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:08:39.151122Z"},"content_sha256":"2863df1df14a2a9948f694001287b84ca8d9736abdfe5a46fde3bb9f87d77437","schema_version":"1.0","event_id":"sha256:2863df1df14a2a9948f694001287b84ca8d9736abdfe5a46fde3bb9f87d77437"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QQ7R6EJW24H43WBTIWMK75L4QR/bundle.json","state_url":"https://pith.science/pith/QQ7R6EJW24H43WBTIWMK75L4QR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QQ7R6EJW24H43WBTIWMK75L4QR/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":"2026-08-04T06:08:39Z","links":{"resolver":"https://pith.science/pith/QQ7R6EJW24H43WBTIWMK75L4QR","bundle":"https://pith.science/pith/QQ7R6EJW24H43WBTIWMK75L4QR/bundle.json","state":"https://pith.science/pith/QQ7R6EJW24H43WBTIWMK75L4QR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QQ7R6EJW24H43WBTIWMK75L4QR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QQ7R6EJW24H43WBTIWMK75L4QR","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":"8f36010afe02f34c913cc7d66c1f8cfb7f7254bef24e630fac76e3a7d382fd91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-15T13:58:07Z","title_canon_sha256":"067447292a53d0d4dad1eb0cd557ed82d41966b67b7ceda1d31e28a5d1eea0e2"},"schema_version":"1.0","source":{"id":"2303.08631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.08631","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"arxiv_version","alias_value":"2303.08631v1","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08631","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"pith_short_12","alias_value":"QQ7R6EJW24H4","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"pith_short_16","alias_value":"QQ7R6EJW24H43WBT","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"pith_short_8","alias_value":"QQ7R6EJW","created_at":"2026-07-05T05:51:35Z"}],"graph_snapshots":[{"event_id":"sha256:2863df1df14a2a9948f694001287b84ca8d9736abdfe5a46fde3bb9f87d77437","target":"graph","created_at":"2026-07-05T05:51:35Z","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/2303.08631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Reinforcement Learning the Q-learning algorithm provably converges to the optimal solution. However, as others have demonstrated, Q-learning can also overestimate the values and thereby spend too long exploring unhelpful states. Double Q-learning is a provably convergent alternative that mitigates some of the overestimation issues, though sometimes at the expense of slower convergence. We introduce an alternative algorithm that replaces the max operation with an average, resulting also in a provably convergent off-policy algorithm which can mitigate overestimation yet retain similar converg","authors_text":"David Barber","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-15T13:58:07Z","title":"Smoothed Q-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08631","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":"sha256:0eb926639b4b021ead2e48fb899a823f7897f7faef387ad16ef6690492f62100","target":"record","created_at":"2026-07-05T05:51:35Z","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":"8f36010afe02f34c913cc7d66c1f8cfb7f7254bef24e630fac76e3a7d382fd91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-15T13:58:07Z","title_canon_sha256":"067447292a53d0d4dad1eb0cd557ed82d41966b67b7ceda1d31e28a5d1eea0e2"},"schema_version":"1.0","source":{"id":"2303.08631","kind":"arxiv","version":1}},"canonical_sha256":"843f1f1136d70fcdd8334598aff57c8461324295a04fc4e608c9eeb43e3721da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"843f1f1136d70fcdd8334598aff57c8461324295a04fc4e608c9eeb43e3721da","first_computed_at":"2026-07-05T05:51:35.324681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:51:35.324681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N2KCLsd/Dbk72buCTIf2zlMiv+AW1hKcSaeNdF8mx+ODQ7aq3buDT4dbruvRHBS3s3AocVYqTHEykcnxSEVUDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:51:35.325103Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.08631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0eb926639b4b021ead2e48fb899a823f7897f7faef387ad16ef6690492f62100","sha256:2863df1df14a2a9948f694001287b84ca8d9736abdfe5a46fde3bb9f87d77437"],"state_sha256":"79d5604890220eb06d1686dbd9a273ae0e170441d94b39a8be3b3a77bd523e87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b9V7zGhxoh5mdIjwHToPvxmbz/I7l0AhnB3Ick1NtHpwwm+M4ltuNFLc93uv79wP2KVwSX0ilsb6v/U5eiPqBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:08:39.155960Z","bundle_sha256":"3dbfa31da59fa5b812313ada55ab45c5ebcb24ba430a67c6e91703a070c09753"}}