{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7RRUHIBX3JCJ25P4JP7DJ2GTRA","short_pith_number":"pith:7RRUHIBX","canonical_record":{"source":{"id":"1802.07842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-21T23:14:44Z","cross_cats_sorted":[],"title_canon_sha256":"a535359e815cd8fdbd83aef16ab5c6b4df858694072850e076293379ed9a2d22","abstract_canon_sha256":"c7d938b5a7cc0c862116ccd921ff16704a51c370fc374a94df9cadff9e430c6d"},"schema_version":"1.0"},"canonical_sha256":"fc6343a037da449d75fc4bfe34e8d3882fecc793c4ae5e572d8dcf1502bdb327","source":{"kind":"arxiv","id":"1802.07842","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07842","created_at":"2026-05-18T00:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07842v1","created_at":"2026-05-18T00:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07842","created_at":"2026-05-18T00:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"7RRUHIBX3JCJ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7RRUHIBX3JCJ25P4","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7RRUHIBX","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7RRUHIBX3JCJ25P4JP7DJ2GTRA","target":"record","payload":{"canonical_record":{"source":{"id":"1802.07842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-21T23:14:44Z","cross_cats_sorted":[],"title_canon_sha256":"a535359e815cd8fdbd83aef16ab5c6b4df858694072850e076293379ed9a2d22","abstract_canon_sha256":"c7d938b5a7cc0c862116ccd921ff16704a51c370fc374a94df9cadff9e430c6d"},"schema_version":"1.0"},"canonical_sha256":"fc6343a037da449d75fc4bfe34e8d3882fecc793c4ae5e572d8dcf1502bdb327","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:48.765325Z","signature_b64":"Qw+mQWL1osB7ujS/QEOA4j753X9ql3CP8thr5riNCk1aL+5OUdY0R+gXdmnyyEWbWE05eCYzAobqF4+jDc71Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc6343a037da449d75fc4bfe34e8d3882fecc793c4ae5e572d8dcf1502bdb327","last_reissued_at":"2026-05-18T00:22:48.764899Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:48.764899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.07842","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":"2026-05-18T00:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kah7DnuBq/5CTMnIBjxdtG4A+60BE6SBHO6GF2l4f1XXMq4dNHz8qB3pYoPnYKtaBLLaVgfEUE5X+GlwkOHLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:17:55.037632Z"},"content_sha256":"5fedd9c076be34940b4006b3aa81e5f3c049891b3b6c4752307613df624f86b9","schema_version":"1.0","event_id":"sha256:5fedd9c076be34940b4006b3aa81e5f3c049891b3b6c4752307613df624f86b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7RRUHIBX3JCJ25P4JP7DJ2GTRA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convergent Actor-Critic Algorithms Under Off-Policy Training and Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hamid Reza Maei","submitted_at":"2018-02-21T23:14:44Z","abstract_excerpt":"We present the first class of policy-gradient algorithms that work with both state-value and policy function-approximation, and are guaranteed to converge under off-policy training. Our solution targets problems in reinforcement learning where the action representation adds to the-curse-of-dimensionality; that is, with continuous or large action sets, thus making it infeasible to estimate state-action value functions (Q functions). Using state-value functions helps to lift the curse and as a result naturally turn our policy-gradient solution into classical Actor-Critic architecture whose Actor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07842","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":"2026-05-18T00:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Y/sCcZszoZmEojavHfJA3ruq62u0D2Tx0bJgkxc266cBF/nsYrgrMcGTMGgK+dA6AhGzpddKCGgZK/Rxf0WAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:17:55.037926Z"},"content_sha256":"9439b1b91ea7144022a0017d42bab40b8e720aaba9f59365166bed1320697d04","schema_version":"1.0","event_id":"sha256:9439b1b91ea7144022a0017d42bab40b8e720aaba9f59365166bed1320697d04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7RRUHIBX3JCJ25P4JP7DJ2GTRA/bundle.json","state_url":"https://pith.science/pith/7RRUHIBX3JCJ25P4JP7DJ2GTRA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7RRUHIBX3JCJ25P4JP7DJ2GTRA/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":"2026-08-20T06:17:55Z","links":{"resolver":"https://pith.science/pith/7RRUHIBX3JCJ25P4JP7DJ2GTRA","bundle":"https://pith.science/pith/7RRUHIBX3JCJ25P4JP7DJ2GTRA/bundle.json","state":"https://pith.science/pith/7RRUHIBX3JCJ25P4JP7DJ2GTRA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7RRUHIBX3JCJ25P4JP7DJ2GTRA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7RRUHIBX3JCJ25P4JP7DJ2GTRA","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":"c7d938b5a7cc0c862116ccd921ff16704a51c370fc374a94df9cadff9e430c6d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-21T23:14:44Z","title_canon_sha256":"a535359e815cd8fdbd83aef16ab5c6b4df858694072850e076293379ed9a2d22"},"schema_version":"1.0","source":{"id":"1802.07842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07842","created_at":"2026-05-18T00:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07842v1","created_at":"2026-05-18T00:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07842","created_at":"2026-05-18T00:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"7RRUHIBX3JCJ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7RRUHIBX3JCJ25P4","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7RRUHIBX","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:9439b1b91ea7144022a0017d42bab40b8e720aaba9f59365166bed1320697d04","target":"graph","created_at":"2026-05-18T00:22:48Z","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":"We present the first class of policy-gradient algorithms that work with both state-value and policy function-approximation, and are guaranteed to converge under off-policy training. Our solution targets problems in reinforcement learning where the action representation adds to the-curse-of-dimensionality; that is, with continuous or large action sets, thus making it infeasible to estimate state-action value functions (Q functions). Using state-value functions helps to lift the curse and as a result naturally turn our policy-gradient solution into classical Actor-Critic architecture whose Actor","authors_text":"Hamid Reza Maei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-21T23:14:44Z","title":"Convergent Actor-Critic Algorithms Under Off-Policy Training and Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07842","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":"sha256:5fedd9c076be34940b4006b3aa81e5f3c049891b3b6c4752307613df624f86b9","target":"record","created_at":"2026-05-18T00:22:48Z","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":"c7d938b5a7cc0c862116ccd921ff16704a51c370fc374a94df9cadff9e430c6d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-21T23:14:44Z","title_canon_sha256":"a535359e815cd8fdbd83aef16ab5c6b4df858694072850e076293379ed9a2d22"},"schema_version":"1.0","source":{"id":"1802.07842","kind":"arxiv","version":1}},"canonical_sha256":"fc6343a037da449d75fc4bfe34e8d3882fecc793c4ae5e572d8dcf1502bdb327","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc6343a037da449d75fc4bfe34e8d3882fecc793c4ae5e572d8dcf1502bdb327","first_computed_at":"2026-05-18T00:22:48.764899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:48.764899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qw+mQWL1osB7ujS/QEOA4j753X9ql3CP8thr5riNCk1aL+5OUdY0R+gXdmnyyEWbWE05eCYzAobqF4+jDc71Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:48.765325Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.07842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fedd9c076be34940b4006b3aa81e5f3c049891b3b6c4752307613df624f86b9","sha256:9439b1b91ea7144022a0017d42bab40b8e720aaba9f59365166bed1320697d04"],"state_sha256":"c5cc7a2d25b18316cc7bc35ef2f875addf1c205e10e4a50dc98423ce99e0aac2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RaDpknpK+wy1dk5FcpKFV5JyvPbhkRKXXqekoJibPbh3xQxW6XrlCnj2t/rmHHbqnpa5WSiWbkh/RLLNpR3nBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T06:17:55.042016Z","bundle_sha256":"3cb8e6da216a652b37d46a0d5198c27be19adf2f2326138517ec377e087b826b"}}