{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:YSPA5TRRUJZCHU5EYSHD6ELBUG","short_pith_number":"pith:YSPA5TRR","canonical_record":{"source":{"id":"1512.04105","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-13T19:20:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fb92655e6dc00483350a1430dc911d93238dcda78d9ad1835b7282a0cbd099a0","abstract_canon_sha256":"ad823b615a1e93162c6648f72a32c0504355e11c2e02908a6c32e01fb4b61897"},"schema_version":"1.0"},"canonical_sha256":"c49e0ece31a27223d3a4c48e3f1161a1b9672b88f007b665b31dda521f337b3d","source":{"kind":"arxiv","id":"1512.04105","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.04105","created_at":"2026-05-18T01:24:23Z"},{"alias_kind":"arxiv_version","alias_value":"1512.04105v1","created_at":"2026-05-18T01:24:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.04105","created_at":"2026-05-18T01:24:23Z"},{"alias_kind":"pith_short_12","alias_value":"YSPA5TRRUJZC","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"YSPA5TRRUJZCHU5E","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"YSPA5TRR","created_at":"2026-05-18T12:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:YSPA5TRRUJZCHU5EYSHD6ELBUG","target":"record","payload":{"canonical_record":{"source":{"id":"1512.04105","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-13T19:20:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fb92655e6dc00483350a1430dc911d93238dcda78d9ad1835b7282a0cbd099a0","abstract_canon_sha256":"ad823b615a1e93162c6648f72a32c0504355e11c2e02908a6c32e01fb4b61897"},"schema_version":"1.0"},"canonical_sha256":"c49e0ece31a27223d3a4c48e3f1161a1b9672b88f007b665b31dda521f337b3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:23.130939Z","signature_b64":"wRX/kH4MwwIuYFY+ksB1ZIUpVAeDNjR0pOUo7ckwr2FO9l41P3rlf1aGlt2nGbLifCHAWvqNZGMxrCnW09P4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c49e0ece31a27223d3a4c48e3f1161a1b9672b88f007b665b31dda521f337b3d","last_reissued_at":"2026-05-18T01:24:23.130451Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:23.130451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.04105","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":"2026-05-18T01:24:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qtV1hQjaKswK148Mdf+Oi+nUORRX2a1ZaNrlUb6zQDLFhYOndO1K85583IpiHy/yRMd2VzoCFOEDwormxhb8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:21:08.074717Z"},"content_sha256":"01f80876387abc50366e6bfafde3b5e29e7b2454f5ae4268c1ba276ea7d015cc","schema_version":"1.0","event_id":"sha256:01f80876387abc50366e6bfafde3b5e29e7b2454f5ae4268c1ba276ea7d015cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:YSPA5TRRUJZCHU5EYSHD6ELBUG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Gradient Methods for Off-policy Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Doina Precup, Lucas Lehnert","submitted_at":"2015-12-13T19:20:14Z","abstract_excerpt":"Off-policy learning refers to the problem of learning the value function of a way of behaving, or policy, while following a different policy. Gradient-based off-policy learning algorithms, such as GTD and TDC/GQ, converge even when using function approximation and incremental updates. However, they have been developed for the case of a fixed behavior policy. In control problems, one would like to adapt the behavior policy over time to become more greedy with respect to the existing value function. In this paper, we present the first gradient-based learning algorithms for this problem, which re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.04105","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":"2026-05-18T01:24:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nwChH1tMRARbZcwJrAWuFcFfKqAQAaOmER+R2xyemQkrW1U73T1x0FmkhmWgw4XcwmITjNikcAvdVmR3qA2wBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:21:08.075401Z"},"content_sha256":"7c09b42999cdee2ab6d04a7989f95db3d29f80f998b414e81855aa37faee2445","schema_version":"1.0","event_id":"sha256:7c09b42999cdee2ab6d04a7989f95db3d29f80f998b414e81855aa37faee2445"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YSPA5TRRUJZCHU5EYSHD6ELBUG/bundle.json","state_url":"https://pith.science/pith/YSPA5TRRUJZCHU5EYSHD6ELBUG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YSPA5TRRUJZCHU5EYSHD6ELBUG/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":"2026-05-25T19:21:08Z","links":{"resolver":"https://pith.science/pith/YSPA5TRRUJZCHU5EYSHD6ELBUG","bundle":"https://pith.science/pith/YSPA5TRRUJZCHU5EYSHD6ELBUG/bundle.json","state":"https://pith.science/pith/YSPA5TRRUJZCHU5EYSHD6ELBUG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YSPA5TRRUJZCHU5EYSHD6ELBUG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:YSPA5TRRUJZCHU5EYSHD6ELBUG","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":"ad823b615a1e93162c6648f72a32c0504355e11c2e02908a6c32e01fb4b61897","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-13T19:20:14Z","title_canon_sha256":"fb92655e6dc00483350a1430dc911d93238dcda78d9ad1835b7282a0cbd099a0"},"schema_version":"1.0","source":{"id":"1512.04105","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.04105","created_at":"2026-05-18T01:24:23Z"},{"alias_kind":"arxiv_version","alias_value":"1512.04105v1","created_at":"2026-05-18T01:24:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.04105","created_at":"2026-05-18T01:24:23Z"},{"alias_kind":"pith_short_12","alias_value":"YSPA5TRRUJZC","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"YSPA5TRRUJZCHU5E","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"YSPA5TRR","created_at":"2026-05-18T12:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:7c09b42999cdee2ab6d04a7989f95db3d29f80f998b414e81855aa37faee2445","target":"graph","created_at":"2026-05-18T01:24:23Z","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":"Off-policy learning refers to the problem of learning the value function of a way of behaving, or policy, while following a different policy. Gradient-based off-policy learning algorithms, such as GTD and TDC/GQ, converge even when using function approximation and incremental updates. However, they have been developed for the case of a fixed behavior policy. In control problems, one would like to adapt the behavior policy over time to become more greedy with respect to the existing value function. In this paper, we present the first gradient-based learning algorithms for this problem, which re","authors_text":"Doina Precup, Lucas Lehnert","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-13T19:20:14Z","title":"Policy Gradient Methods for Off-policy Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.04105","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":"sha256:01f80876387abc50366e6bfafde3b5e29e7b2454f5ae4268c1ba276ea7d015cc","target":"record","created_at":"2026-05-18T01:24:23Z","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":"ad823b615a1e93162c6648f72a32c0504355e11c2e02908a6c32e01fb4b61897","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-13T19:20:14Z","title_canon_sha256":"fb92655e6dc00483350a1430dc911d93238dcda78d9ad1835b7282a0cbd099a0"},"schema_version":"1.0","source":{"id":"1512.04105","kind":"arxiv","version":1}},"canonical_sha256":"c49e0ece31a27223d3a4c48e3f1161a1b9672b88f007b665b31dda521f337b3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c49e0ece31a27223d3a4c48e3f1161a1b9672b88f007b665b31dda521f337b3d","first_computed_at":"2026-05-18T01:24:23.130451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:24:23.130451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wRX/kH4MwwIuYFY+ksB1ZIUpVAeDNjR0pOUo7ckwr2FO9l41P3rlf1aGlt2nGbLifCHAWvqNZGMxrCnW09P4AA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:24:23.130939Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.04105","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01f80876387abc50366e6bfafde3b5e29e7b2454f5ae4268c1ba276ea7d015cc","sha256:7c09b42999cdee2ab6d04a7989f95db3d29f80f998b414e81855aa37faee2445"],"state_sha256":"6403ee55de3d692cdb4cc4ac31c91be504598aba8d60942264cea7924979289c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ykAGvRQzYdTiTiw8SA+Dda5Vxpra9yuqVgfLYEuHII4oeeDfA4RlFVsSTJcsmsWfR6sxJ4TpuewHhhujB+iwDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:21:08.079146Z","bundle_sha256":"0452019772a5d5642ef92719d389901cb80015da9752afae83fc3dd4e1230cb8"}}