{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RDLG6OTT76EH7Y7N3K5ZTFBT6A","short_pith_number":"pith:RDLG6OTT","canonical_record":{"source":{"id":"1802.03171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-09T08:46:21Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"668c01be78064b9abb433c2165a43fe676fbbc0e9fef3ef3226294c5026e9f3b","abstract_canon_sha256":"72dc557adf4cc4384c43c07a8b30e27ddb4ff72fd3924f52781e281ddaa3821a"},"schema_version":"1.0"},"canonical_sha256":"88d66f3a73ff887fe3eddabb999433f0251c0160cc5b910b8be852e317c9994a","source":{"kind":"arxiv","id":"1802.03171","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03171","created_at":"2026-05-18T00:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03171v1","created_at":"2026-05-18T00:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03171","created_at":"2026-05-18T00:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"RDLG6OTT76EH","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RDLG6OTT76EH7Y7N","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RDLG6OTT","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RDLG6OTT76EH7Y7N3K5ZTFBT6A","target":"record","payload":{"canonical_record":{"source":{"id":"1802.03171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-09T08:46:21Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"668c01be78064b9abb433c2165a43fe676fbbc0e9fef3ef3226294c5026e9f3b","abstract_canon_sha256":"72dc557adf4cc4384c43c07a8b30e27ddb4ff72fd3924f52781e281ddaa3821a"},"schema_version":"1.0"},"canonical_sha256":"88d66f3a73ff887fe3eddabb999433f0251c0160cc5b910b8be852e317c9994a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:58.393234Z","signature_b64":"1Mc5SlrUhfKBKmjJ0QLcXkA9/IKMbo9a6OovlVoL+EOqTuQ3IxyQuxk3lZOcdJAt7GEYZRJbGSvoCXFiWj7rDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88d66f3a73ff887fe3eddabb999433f0251c0160cc5b910b8be852e317c9994a","last_reissued_at":"2026-05-18T00:23:58.392751Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:58.392751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.03171","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":"2026-05-18T00:23:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u5AJt9yfwN9Y7Xi0aIh5Bscz34Lda8kkDF5nmHUuGN8A8pr8OdUHCMnH3ceVt6jVlCm53NpwgYAvFXAXPdwgDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:10:09.129223Z"},"content_sha256":"160110153fcbd83558653077fe855c67b5451fd8a083258faae9b88feed1c33d","schema_version":"1.0","event_id":"sha256:160110153fcbd83558653077fe855c67b5451fd8a083258faae9b88feed1c33d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RDLG6OTT76EH7Y7N3K5ZTFBT6A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Unified Approach for Multi-step Temporal-Difference Learning with Eligibility Traces in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Gang Pan, Long Yang, Minhao Shi, Qian Zheng, Wenjia Meng","submitted_at":"2018-02-09T08:46:21Z","abstract_excerpt":"Recently, a new multi-step temporal learning algorithm, called $Q(\\sigma)$, unifies $n$-step Tree-Backup (when $\\sigma=0$) and $n$-step Sarsa (when $\\sigma=1$) by introducing a sampling parameter $\\sigma$. However, similar to other multi-step temporal-difference learning algorithms, $Q(\\sigma)$ needs much memory consumption and computation time. Eligibility trace is an important mechanism to transform the off-line updates into efficient on-line ones which consume less memory and computation time. In this paper, we further develop the original $Q(\\sigma)$, combine it with eligibility traces and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03171","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":"2026-05-18T00:23:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L6MBw3v1xvsgJnPxKu4ZCcsvyU4Rc/IuS4hYXtwFZ6zR56Moh1RdKkxQEkXOSQyRVZwd9KAMkguT9r6hM8uODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:10:09.129701Z"},"content_sha256":"33a45ee50138ea78b70e4b67a994654db2a8f0d8553dd4d98e35d0383b4cc301","schema_version":"1.0","event_id":"sha256:33a45ee50138ea78b70e4b67a994654db2a8f0d8553dd4d98e35d0383b4cc301"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A/bundle.json","state_url":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A/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":"2026-08-14T14:10:09Z","links":{"resolver":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A","bundle":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A/bundle.json","state":"https://pith.science/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RDLG6OTT76EH7Y7N3K5ZTFBT6A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RDLG6OTT76EH7Y7N3K5ZTFBT6A","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":"72dc557adf4cc4384c43c07a8b30e27ddb4ff72fd3924f52781e281ddaa3821a","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-09T08:46:21Z","title_canon_sha256":"668c01be78064b9abb433c2165a43fe676fbbc0e9fef3ef3226294c5026e9f3b"},"schema_version":"1.0","source":{"id":"1802.03171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03171","created_at":"2026-05-18T00:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03171v1","created_at":"2026-05-18T00:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03171","created_at":"2026-05-18T00:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"RDLG6OTT76EH","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RDLG6OTT76EH7Y7N","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RDLG6OTT","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:33a45ee50138ea78b70e4b67a994654db2a8f0d8553dd4d98e35d0383b4cc301","target":"graph","created_at":"2026-05-18T00:23:58Z","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":"Recently, a new multi-step temporal learning algorithm, called $Q(\\sigma)$, unifies $n$-step Tree-Backup (when $\\sigma=0$) and $n$-step Sarsa (when $\\sigma=1$) by introducing a sampling parameter $\\sigma$. However, similar to other multi-step temporal-difference learning algorithms, $Q(\\sigma)$ needs much memory consumption and computation time. Eligibility trace is an important mechanism to transform the off-line updates into efficient on-line ones which consume less memory and computation time. In this paper, we further develop the original $Q(\\sigma)$, combine it with eligibility traces and","authors_text":"Gang Pan, Long Yang, Minhao Shi, Qian Zheng, Wenjia Meng","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-09T08:46:21Z","title":"A Unified Approach for Multi-step Temporal-Difference Learning with Eligibility Traces in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03171","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":"sha256:160110153fcbd83558653077fe855c67b5451fd8a083258faae9b88feed1c33d","target":"record","created_at":"2026-05-18T00:23:58Z","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":"72dc557adf4cc4384c43c07a8b30e27ddb4ff72fd3924f52781e281ddaa3821a","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-09T08:46:21Z","title_canon_sha256":"668c01be78064b9abb433c2165a43fe676fbbc0e9fef3ef3226294c5026e9f3b"},"schema_version":"1.0","source":{"id":"1802.03171","kind":"arxiv","version":1}},"canonical_sha256":"88d66f3a73ff887fe3eddabb999433f0251c0160cc5b910b8be852e317c9994a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88d66f3a73ff887fe3eddabb999433f0251c0160cc5b910b8be852e317c9994a","first_computed_at":"2026-05-18T00:23:58.392751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:58.392751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Mc5SlrUhfKBKmjJ0QLcXkA9/IKMbo9a6OovlVoL+EOqTuQ3IxyQuxk3lZOcdJAt7GEYZRJbGSvoCXFiWj7rDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:58.393234Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.03171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:160110153fcbd83558653077fe855c67b5451fd8a083258faae9b88feed1c33d","sha256:33a45ee50138ea78b70e4b67a994654db2a8f0d8553dd4d98e35d0383b4cc301"],"state_sha256":"991b0ea42306493e6d479f6116b7fd4d14400d5d9ae8584bc1e4b6494e50486a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dtwpr8xKatmOSWJphOVZl4PdDk4fjh6/RNC9GDgY8silgzZzJzfzsbz/dEiJ+aC2bQmrl4pB7Pk1Y8tdnCQnDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T14:10:09.134065Z","bundle_sha256":"6c618c5b2747fb750fdd1ab52c22f8366737f614f1e31044b1663166c311891b"}}