{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:B3HBUKNWMU6B4IRGJ7I4GOQXKU","short_pith_number":"pith:B3HBUKNW","canonical_record":{"source":{"id":"2405.18289","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T15:42:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1f64ed51ca0dad749d3a884e09d62f7b38bf82fb929ef1c15c9bafee9cd25c6c","abstract_canon_sha256":"171ebf18afbd6a1a0013c2fce4253a9eb8c523ff9de3219f99f330ed5096fc41"},"schema_version":"1.0"},"canonical_sha256":"0ece1a29b6653c1e22264fd1c33a175539e61f77231377d39d540b15f11004e8","source":{"kind":"arxiv","id":"2405.18289","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18289","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18289v1","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18289","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"B3HBUKNWMU6B","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"B3HBUKNWMU6B4IRG","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"B3HBUKNW","created_at":"2026-07-05T08:24:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:B3HBUKNWMU6B4IRGJ7I4GOQXKU","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18289","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T15:42:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1f64ed51ca0dad749d3a884e09d62f7b38bf82fb929ef1c15c9bafee9cd25c6c","abstract_canon_sha256":"171ebf18afbd6a1a0013c2fce4253a9eb8c523ff9de3219f99f330ed5096fc41"},"schema_version":"1.0"},"canonical_sha256":"0ece1a29b6653c1e22264fd1c33a175539e61f77231377d39d540b15f11004e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:18.030380Z","signature_b64":"ppMzxLMlOHaufLTYS3sNIsBlpR6NgzgB8aF9NugF8n8BnRXQs33putDX3QeTvIK22fAHrUSaYrkXk+g999+KBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ece1a29b6653c1e22264fd1c33a175539e61f77231377d39d540b15f11004e8","last_reissued_at":"2026-07-05T08:24:18.029995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:18.029995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18289","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":"2026-07-05T08:24:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eeg6lFacMhYmVih8Uuzbf3I7y1YsATLHHQaqdIHPr/IulDU2QgU606qw1TslTCkDrdF9WbwJbO7/kpUNnK5BAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:18:19.164640Z"},"content_sha256":"6614aa8e44dc3320632b87ef7fd5ea5111ade0838c69b5ecad8bab4ba0094aba","schema_version":"1.0","event_id":"sha256:6614aa8e44dc3320632b87ef7fd5ea5111ade0838c69b5ecad8bab4ba0094aba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:B3HBUKNWMU6B4IRGJ7I4GOQXKU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Highway Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Francesco Faccio, Haozhe Liu, J\\\"urgen Schmidhuber, Micha{\\l} Grudzie\\'n, Miroslav Strupl, Qingyuan Wu, Xiaoyang Tan, Yuhui Wang","submitted_at":"2024-05-28T15:42:45Z","abstract_excerpt":"Learning from multi-step off-policy data collected by a set of policies is a core problem of reinforcement learning (RL). Approaches based on importance sampling (IS) often suffer from large variances due to products of IS ratios. Typical IS-free methods, such as $n$-step Q-learning, look ahead for $n$ time steps along the trajectory of actions (where $n$ is called the lookahead depth) and utilize off-policy data directly without any additional adjustment. They work well for proper choices of $n$. We show, however, that such IS-free methods underestimate the optimal value function (VF), especi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18289","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/2405.18289/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":"2026-07-05T08:24:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jwxVJswwqP58tx087pRlrFCjcA7Qb+pF83uZ1tSQq6nqD7ahUAG7eWM1b6dNTUTB/3wVUsrF08vhI9FWgWGDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:18:19.165142Z"},"content_sha256":"aab7a43c6d31d6fb8cc43aa1e7005be8d2668c6796f96291db6699da96ded593","schema_version":"1.0","event_id":"sha256:aab7a43c6d31d6fb8cc43aa1e7005be8d2668c6796f96291db6699da96ded593"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B3HBUKNWMU6B4IRGJ7I4GOQXKU/bundle.json","state_url":"https://pith.science/pith/B3HBUKNWMU6B4IRGJ7I4GOQXKU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B3HBUKNWMU6B4IRGJ7I4GOQXKU/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":"2026-08-04T16:18:19Z","links":{"resolver":"https://pith.science/pith/B3HBUKNWMU6B4IRGJ7I4GOQXKU","bundle":"https://pith.science/pith/B3HBUKNWMU6B4IRGJ7I4GOQXKU/bundle.json","state":"https://pith.science/pith/B3HBUKNWMU6B4IRGJ7I4GOQXKU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B3HBUKNWMU6B4IRGJ7I4GOQXKU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B3HBUKNWMU6B4IRGJ7I4GOQXKU","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":"171ebf18afbd6a1a0013c2fce4253a9eb8c523ff9de3219f99f330ed5096fc41","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T15:42:45Z","title_canon_sha256":"1f64ed51ca0dad749d3a884e09d62f7b38bf82fb929ef1c15c9bafee9cd25c6c"},"schema_version":"1.0","source":{"id":"2405.18289","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18289","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18289v1","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18289","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"B3HBUKNWMU6B","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"B3HBUKNWMU6B4IRG","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"B3HBUKNW","created_at":"2026-07-05T08:24:18Z"}],"graph_snapshots":[{"event_id":"sha256:aab7a43c6d31d6fb8cc43aa1e7005be8d2668c6796f96291db6699da96ded593","target":"graph","created_at":"2026-07-05T08:24:18Z","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/2405.18289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from multi-step off-policy data collected by a set of policies is a core problem of reinforcement learning (RL). Approaches based on importance sampling (IS) often suffer from large variances due to products of IS ratios. Typical IS-free methods, such as $n$-step Q-learning, look ahead for $n$ time steps along the trajectory of actions (where $n$ is called the lookahead depth) and utilize off-policy data directly without any additional adjustment. They work well for proper choices of $n$. We show, however, that such IS-free methods underestimate the optimal value function (VF), especi","authors_text":"Francesco Faccio, Haozhe Liu, J\\\"urgen Schmidhuber, Micha{\\l} Grudzie\\'n, Miroslav Strupl, Qingyuan Wu, Xiaoyang Tan, Yuhui Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T15:42:45Z","title":"Highway Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18289","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":"sha256:6614aa8e44dc3320632b87ef7fd5ea5111ade0838c69b5ecad8bab4ba0094aba","target":"record","created_at":"2026-07-05T08:24:18Z","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":"171ebf18afbd6a1a0013c2fce4253a9eb8c523ff9de3219f99f330ed5096fc41","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T15:42:45Z","title_canon_sha256":"1f64ed51ca0dad749d3a884e09d62f7b38bf82fb929ef1c15c9bafee9cd25c6c"},"schema_version":"1.0","source":{"id":"2405.18289","kind":"arxiv","version":1}},"canonical_sha256":"0ece1a29b6653c1e22264fd1c33a175539e61f77231377d39d540b15f11004e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ece1a29b6653c1e22264fd1c33a175539e61f77231377d39d540b15f11004e8","first_computed_at":"2026-07-05T08:24:18.029995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:18.029995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ppMzxLMlOHaufLTYS3sNIsBlpR6NgzgB8aF9NugF8n8BnRXQs33putDX3QeTvIK22fAHrUSaYrkXk+g999+KBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:18.030380Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18289","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6614aa8e44dc3320632b87ef7fd5ea5111ade0838c69b5ecad8bab4ba0094aba","sha256:aab7a43c6d31d6fb8cc43aa1e7005be8d2668c6796f96291db6699da96ded593"],"state_sha256":"c51b104095ac214e4195a289bf3790eec98158834238e0b6f415aa32f9d27287"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HXMsLNkVKVo9yJexw5BBDDtxyvQo1JNR0AnxVdVEwbhdMd83+VjYtFVmctVGVYD9vP/1UGX84FB0ofbCQ2hwBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:18:19.169319Z","bundle_sha256":"f7f763dc6cef47db657d11c0dc645198653590d767db81bc9de1c4ea3cf3e841"}}