{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:6DUCH5DH2FLRULCTSIOTJJFMFS","short_pith_number":"pith:6DUCH5DH","canonical_record":{"source":{"id":"1703.05820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-16T21:08:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0a5f54fd7a853f9cd18a58a113f173e38e5718073a213f45533b076fde53256c","abstract_canon_sha256":"58979d4027405161d713b034276f6c02500895952dffdabf18a8cffbb8abed73"},"schema_version":"1.0"},"canonical_sha256":"f0e823f467d1571a2c53921d34a4ac2c8e6556a248f62ff0b9d2476b279a685c","source":{"kind":"arxiv","id":"1703.05820","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.05820","created_at":"2026-05-18T00:48:32Z"},{"alias_kind":"arxiv_version","alias_value":"1703.05820v1","created_at":"2026-05-18T00:48:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.05820","created_at":"2026-05-18T00:48:32Z"},{"alias_kind":"pith_short_12","alias_value":"6DUCH5DH2FLR","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6DUCH5DH2FLRULCT","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6DUCH5DH","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:6DUCH5DH2FLRULCTSIOTJJFMFS","target":"record","payload":{"canonical_record":{"source":{"id":"1703.05820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-16T21:08:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0a5f54fd7a853f9cd18a58a113f173e38e5718073a213f45533b076fde53256c","abstract_canon_sha256":"58979d4027405161d713b034276f6c02500895952dffdabf18a8cffbb8abed73"},"schema_version":"1.0"},"canonical_sha256":"f0e823f467d1571a2c53921d34a4ac2c8e6556a248f62ff0b9d2476b279a685c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:32.002406Z","signature_b64":"ta5RAdIGSqMxrntfP+SSsE29+vfXqjNRxIA6dqTzkchjT2EudnTYkSdyLBxiU57W/Z1ddwfgEUA8VKYUMnckBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0e823f467d1571a2c53921d34a4ac2c8e6556a248f62ff0b9d2476b279a685c","last_reissued_at":"2026-05-18T00:48:32.001967Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:32.001967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.05820","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":"2026-05-18T00:48:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UuuLGY0KCWbKbyAzhHDNDpgD1w8WzCWQSTavGcztsGUvhWOfu1osTeeKwlb70KjB98Z+X5tMK8Lw6KakOe8EAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:19:18.144447Z"},"content_sha256":"1dd8879a0ec5dd09cb2acbd5a12268f58af4b6de767d9b547c517337a9f35a12","schema_version":"1.0","event_id":"sha256:1dd8879a0ec5dd09cb2acbd5a12268f58af4b6de767d9b547c517337a9f35a12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:6DUCH5DH2FLRULCTSIOTJJFMFS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Particle Value Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andriy Mnih, Arnaud Doucet, Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Yee Whye Teh","submitted_at":"2017-03-16T21:08:31Z","abstract_excerpt":"The policy gradients of the expected return objective can react slowly to rare rewards. Yet, in some cases agents may wish to emphasize the low or high returns regardless of their probability. Borrowing from the economics and control literature, we review the risk-sensitive value function that arises from an exponential utility and illustrate its effects on an example. This risk-sensitive value function is not always applicable to reinforcement learning problems, so we introduce the particle value function defined by a particle filter over the distributions of an agent's experience, which boun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.05820","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":"2026-05-18T00:48:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w4vR8ALlcnO5n6tPmqv4TvApXnRAZvSAZ7hGsYME7dFBiN5459Hm2OoJXzXqmhXckMjmJVzTWnj/yjr0+sDFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:19:18.145091Z"},"content_sha256":"d13af60510e9303d2bc000c24b2285e2ff1d446dd41e2136575e7b40eed362be","schema_version":"1.0","event_id":"sha256:d13af60510e9303d2bc000c24b2285e2ff1d446dd41e2136575e7b40eed362be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6DUCH5DH2FLRULCTSIOTJJFMFS/bundle.json","state_url":"https://pith.science/pith/6DUCH5DH2FLRULCTSIOTJJFMFS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6DUCH5DH2FLRULCTSIOTJJFMFS/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":"2026-05-26T20:19:18Z","links":{"resolver":"https://pith.science/pith/6DUCH5DH2FLRULCTSIOTJJFMFS","bundle":"https://pith.science/pith/6DUCH5DH2FLRULCTSIOTJJFMFS/bundle.json","state":"https://pith.science/pith/6DUCH5DH2FLRULCTSIOTJJFMFS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6DUCH5DH2FLRULCTSIOTJJFMFS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:6DUCH5DH2FLRULCTSIOTJJFMFS","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":"58979d4027405161d713b034276f6c02500895952dffdabf18a8cffbb8abed73","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-16T21:08:31Z","title_canon_sha256":"0a5f54fd7a853f9cd18a58a113f173e38e5718073a213f45533b076fde53256c"},"schema_version":"1.0","source":{"id":"1703.05820","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.05820","created_at":"2026-05-18T00:48:32Z"},{"alias_kind":"arxiv_version","alias_value":"1703.05820v1","created_at":"2026-05-18T00:48:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.05820","created_at":"2026-05-18T00:48:32Z"},{"alias_kind":"pith_short_12","alias_value":"6DUCH5DH2FLR","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6DUCH5DH2FLRULCT","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6DUCH5DH","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:d13af60510e9303d2bc000c24b2285e2ff1d446dd41e2136575e7b40eed362be","target":"graph","created_at":"2026-05-18T00:48:32Z","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":"The policy gradients of the expected return objective can react slowly to rare rewards. Yet, in some cases agents may wish to emphasize the low or high returns regardless of their probability. Borrowing from the economics and control literature, we review the risk-sensitive value function that arises from an exponential utility and illustrate its effects on an example. This risk-sensitive value function is not always applicable to reinforcement learning problems, so we introduce the particle value function defined by a particle filter over the distributions of an agent's experience, which boun","authors_text":"Andriy Mnih, Arnaud Doucet, Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Yee Whye Teh","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-16T21:08:31Z","title":"Particle Value Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.05820","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":"sha256:1dd8879a0ec5dd09cb2acbd5a12268f58af4b6de767d9b547c517337a9f35a12","target":"record","created_at":"2026-05-18T00:48:32Z","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":"58979d4027405161d713b034276f6c02500895952dffdabf18a8cffbb8abed73","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-16T21:08:31Z","title_canon_sha256":"0a5f54fd7a853f9cd18a58a113f173e38e5718073a213f45533b076fde53256c"},"schema_version":"1.0","source":{"id":"1703.05820","kind":"arxiv","version":1}},"canonical_sha256":"f0e823f467d1571a2c53921d34a4ac2c8e6556a248f62ff0b9d2476b279a685c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0e823f467d1571a2c53921d34a4ac2c8e6556a248f62ff0b9d2476b279a685c","first_computed_at":"2026-05-18T00:48:32.001967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:32.001967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ta5RAdIGSqMxrntfP+SSsE29+vfXqjNRxIA6dqTzkchjT2EudnTYkSdyLBxiU57W/Z1ddwfgEUA8VKYUMnckBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:32.002406Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.05820","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dd8879a0ec5dd09cb2acbd5a12268f58af4b6de767d9b547c517337a9f35a12","sha256:d13af60510e9303d2bc000c24b2285e2ff1d446dd41e2136575e7b40eed362be"],"state_sha256":"8b6bb4f41b5fcc92405577d5fc7fc841675794bcdcd1bc43a0717549b6a821c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Te/vnJgWNULGVi3Ic6m8v7m02x83stXeb7oFGUZZBSql0k3d+5nv63/Z2jT2T8Up9mlhzt6skbMd7YbvrouEDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T20:19:18.148326Z","bundle_sha256":"b7642b9c7f3b1b42f4bd27ca1132ea7ec2d01e65208ece62ab60ea8dacbc8c16"}}