{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RVHDCYU5JF5WT42DSQK4MHMAJT","short_pith_number":"pith:RVHDCYU5","canonical_record":{"source":{"id":"1804.07323","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-19T18:24:18Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"a587e227ddefad2d0e9fbbf07b4f83e42edc86cebffa0bedc53a9578d8e7847e","abstract_canon_sha256":"22da1d4e5816927b2c40c870ee754a969924b9436fc2d1d9d5792f7da37764a6"},"schema_version":"1.0"},"canonical_sha256":"8d4e31629d497b69f3439415c61d804cf34ec5c3e832aec8ed645f71b790524d","source":{"kind":"arxiv","id":"1804.07323","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07323","created_at":"2026-05-18T00:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07323v1","created_at":"2026-05-18T00:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07323","created_at":"2026-05-18T00:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"RVHDCYU5JF5W","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RVHDCYU5JF5WT42D","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RVHDCYU5","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RVHDCYU5JF5WT42DSQK4MHMAJT","target":"record","payload":{"canonical_record":{"source":{"id":"1804.07323","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-19T18:24:18Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"a587e227ddefad2d0e9fbbf07b4f83e42edc86cebffa0bedc53a9578d8e7847e","abstract_canon_sha256":"22da1d4e5816927b2c40c870ee754a969924b9436fc2d1d9d5792f7da37764a6"},"schema_version":"1.0"},"canonical_sha256":"8d4e31629d497b69f3439415c61d804cf34ec5c3e832aec8ed645f71b790524d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:59.159685Z","signature_b64":"cyjDx/M6kO+kIaTPvfgv3sS6AKlb/Hbe2EG3SPGwhymFhvzA0VudTO4PgZCus06jeCbOKpcbNAuU0W1In/dJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d4e31629d497b69f3439415c61d804cf34ec5c3e832aec8ed645f71b790524d","last_reissued_at":"2026-05-18T00:17:59.158995Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:59.158995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.07323","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":"2026-05-18T00:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z2yoNECF8WAGXLNirCEQkQFhpM1Udn8smWw5dZXjd95/tI6roOpPdMdk9MCMzcctf3IpQAzPShSB8jgql9unCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T13:29:12.811853Z"},"content_sha256":"e6cb3c04704911cd1139b309d51c4fdcd589a550493fec48acb881b15e58028b","schema_version":"1.0","event_id":"sha256:e6cb3c04704911cd1139b309d51c4fdcd589a550493fec48acb881b15e58028b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RVHDCYU5JF5WT42DSQK4MHMAJT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alec Koppel, Alejandro Ribeiro, Ekaterina Tolstaya, Ethan Stump","submitted_at":"2018-04-19T18:24:18Z","abstract_excerpt":"We consider Markov Decision Problems defined over continuous state and action spaces, where an autonomous agent seeks to learn a map from its states to actions so as to maximize its long-term discounted accumulation of rewards. We address this problem by considering Bellman's optimality equation defined over action-value functions, which we reformulate into a nested non-convex stochastic optimization problem defined over a Reproducing Kernel Hilbert Space (RKHS). We develop a functional generalization of stochastic quasi-gradient method to solve it, which, owing to the structure of the RKHS, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07323","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":"2026-05-18T00:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M4sa92jEg8b81bGsiZzYt3JbKaIQh8fe78zaUIAmhsYI3GBSNDOIx+1gnOQkOuZxo5fXIaUaCznfr2WW4ze7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T13:29:12.812278Z"},"content_sha256":"43a0f47e864d9c61322cdd6472ac620b4efe41e7fe096334c9d9cbbb8878b08a","schema_version":"1.0","event_id":"sha256:43a0f47e864d9c61322cdd6472ac620b4efe41e7fe096334c9d9cbbb8878b08a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RVHDCYU5JF5WT42DSQK4MHMAJT/bundle.json","state_url":"https://pith.science/pith/RVHDCYU5JF5WT42DSQK4MHMAJT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RVHDCYU5JF5WT42DSQK4MHMAJT/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":"2026-06-27T13:29:12Z","links":{"resolver":"https://pith.science/pith/RVHDCYU5JF5WT42DSQK4MHMAJT","bundle":"https://pith.science/pith/RVHDCYU5JF5WT42DSQK4MHMAJT/bundle.json","state":"https://pith.science/pith/RVHDCYU5JF5WT42DSQK4MHMAJT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RVHDCYU5JF5WT42DSQK4MHMAJT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RVHDCYU5JF5WT42DSQK4MHMAJT","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":"22da1d4e5816927b2c40c870ee754a969924b9436fc2d1d9d5792f7da37764a6","cross_cats_sorted":["cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-19T18:24:18Z","title_canon_sha256":"a587e227ddefad2d0e9fbbf07b4f83e42edc86cebffa0bedc53a9578d8e7847e"},"schema_version":"1.0","source":{"id":"1804.07323","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07323","created_at":"2026-05-18T00:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07323v1","created_at":"2026-05-18T00:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07323","created_at":"2026-05-18T00:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"RVHDCYU5JF5W","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RVHDCYU5JF5WT42D","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RVHDCYU5","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:43a0f47e864d9c61322cdd6472ac620b4efe41e7fe096334c9d9cbbb8878b08a","target":"graph","created_at":"2026-05-18T00:17:59Z","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 consider Markov Decision Problems defined over continuous state and action spaces, where an autonomous agent seeks to learn a map from its states to actions so as to maximize its long-term discounted accumulation of rewards. We address this problem by considering Bellman's optimality equation defined over action-value functions, which we reformulate into a nested non-convex stochastic optimization problem defined over a Reproducing Kernel Hilbert Space (RKHS). We develop a functional generalization of stochastic quasi-gradient method to solve it, which, owing to the structure of the RKHS, a","authors_text":"Alec Koppel, Alejandro Ribeiro, Ekaterina Tolstaya, Ethan Stump","cross_cats":["cs.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-19T18:24:18Z","title":"Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07323","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:e6cb3c04704911cd1139b309d51c4fdcd589a550493fec48acb881b15e58028b","target":"record","created_at":"2026-05-18T00:17:59Z","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":"22da1d4e5816927b2c40c870ee754a969924b9436fc2d1d9d5792f7da37764a6","cross_cats_sorted":["cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-19T18:24:18Z","title_canon_sha256":"a587e227ddefad2d0e9fbbf07b4f83e42edc86cebffa0bedc53a9578d8e7847e"},"schema_version":"1.0","source":{"id":"1804.07323","kind":"arxiv","version":1}},"canonical_sha256":"8d4e31629d497b69f3439415c61d804cf34ec5c3e832aec8ed645f71b790524d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d4e31629d497b69f3439415c61d804cf34ec5c3e832aec8ed645f71b790524d","first_computed_at":"2026-05-18T00:17:59.158995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:59.158995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cyjDx/M6kO+kIaTPvfgv3sS6AKlb/Hbe2EG3SPGwhymFhvzA0VudTO4PgZCus06jeCbOKpcbNAuU0W1In/dJBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:59.159685Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.07323","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6cb3c04704911cd1139b309d51c4fdcd589a550493fec48acb881b15e58028b","sha256:43a0f47e864d9c61322cdd6472ac620b4efe41e7fe096334c9d9cbbb8878b08a"],"state_sha256":"5810fc34f120057c925995ca34fd8646d57a74125f875e758b3053b5b6115fe7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4tLimWDAh5WTr38UxsABjaO1j9vNgHbp4+NI0v8hxATAZLTI76GxSsBjEtp73lmxCXLtPx0SHWYAv9LUmeZIDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T13:29:12.814366Z","bundle_sha256":"1995c0548349ad786f8a3d2efa561fa23ee42a2fbc7e0daf048984055f6a48ba"}}