{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XHSYMPLYVVTR33HE7INTSYXPKZ","short_pith_number":"pith:XHSYMPLY","canonical_record":{"source":{"id":"2110.09712","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T03:35:01Z","cross_cats_sorted":[],"title_canon_sha256":"7974260b7d5318cd513d2e245b98fbe739908f9c07682e9bfe9044b1afc1e101","abstract_canon_sha256":"82ebc1026c65885c0c841d8688453097f80095d6cd0349eceb815e8071c6a0e4"},"schema_version":"1.0"},"canonical_sha256":"b9e5863d78ad671dece4fa1b3962ef566c20dba285175d514b54bd98616c3052","source":{"kind":"arxiv","id":"2110.09712","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.09712","created_at":"2026-07-05T05:10:35Z"},{"alias_kind":"arxiv_version","alias_value":"2110.09712v6","created_at":"2026-07-05T05:10:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09712","created_at":"2026-07-05T05:10:35Z"},{"alias_kind":"pith_short_12","alias_value":"XHSYMPLYVVTR","created_at":"2026-07-05T05:10:35Z"},{"alias_kind":"pith_short_16","alias_value":"XHSYMPLYVVTR33HE","created_at":"2026-07-05T05:10:35Z"},{"alias_kind":"pith_short_8","alias_value":"XHSYMPLY","created_at":"2026-07-05T05:10:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XHSYMPLYVVTR33HE7INTSYXPKZ","target":"record","payload":{"canonical_record":{"source":{"id":"2110.09712","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T03:35:01Z","cross_cats_sorted":[],"title_canon_sha256":"7974260b7d5318cd513d2e245b98fbe739908f9c07682e9bfe9044b1afc1e101","abstract_canon_sha256":"82ebc1026c65885c0c841d8688453097f80095d6cd0349eceb815e8071c6a0e4"},"schema_version":"1.0"},"canonical_sha256":"b9e5863d78ad671dece4fa1b3962ef566c20dba285175d514b54bd98616c3052","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:35.093886Z","signature_b64":"wkVxiOdGjtzG7NyTmgtYU8vlCHioD0aAsaHC1/qRUzUbr0MhWG+32zPQVTWfE/2mHK3pUYKKJVIQvDsneqDFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9e5863d78ad671dece4fa1b3962ef566c20dba285175d514b54bd98616c3052","last_reissued_at":"2026-07-05T05:10:35.093442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:35.093442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.09712","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:10:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l/fCbw+C4D2h+XldsiKUx3W4df6l19J3faGOfqqhj47F4BfFPUXS3vC12J1xpTxirmXcVo0+xzymRXQvqdHSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T10:09:47.017934Z"},"content_sha256":"e119f09e51838083bb6eb8aae9e91b86fc7d4d0d80c94ecf54364e0b3909ac20","schema_version":"1.0","event_id":"sha256:e119f09e51838083bb6eb8aae9e91b86fc7d4d0d80c94ecf54364e0b3909ac20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XHSYMPLYVVTR33HE7INTSYXPKZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Balancing Value Underestimation and Overestimation with Realistic Actor-Critic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gang Wang, Qinyun Tang, Sicen Li, Xinmeng Ma, Yiming Pang","submitted_at":"2021-10-19T03:35:01Z","abstract_excerpt":"Model-free deep reinforcement learning (RL) has been successfully applied to challenging continuous control domains. However, poor sample efficiency prevents these methods from being widely used in real-world domains. This paper introduces a novel model-free algorithm, Realistic Actor-Critic(RAC), which can be incorporated with any off-policy RL algorithms to improve sample efficiency. RAC employs Universal Value Function Approximators (UVFA) to simultaneously learn a policy family with the same neural network, each with different trade-offs between underestimation and overestimation. To learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09712","kind":"arxiv","version":6},"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/2110.09712/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":"2026-07-05T05:10:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sb4Fqqi/WxerpDXyXzL7P36hA5v/haDCet7oKiEHTd3TcmjPWwRLkdlZOf3RUuqplYnq3uyX4RWCFQUtKkQACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T10:09:47.018296Z"},"content_sha256":"1eb98f94601aaaf41611a8e1447e637263e322c7e1636b0651ce54771600ecdd","schema_version":"1.0","event_id":"sha256:1eb98f94601aaaf41611a8e1447e637263e322c7e1636b0651ce54771600ecdd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XHSYMPLYVVTR33HE7INTSYXPKZ/bundle.json","state_url":"https://pith.science/pith/XHSYMPLYVVTR33HE7INTSYXPKZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XHSYMPLYVVTR33HE7INTSYXPKZ/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":"2026-07-17T10:09:47Z","links":{"resolver":"https://pith.science/pith/XHSYMPLYVVTR33HE7INTSYXPKZ","bundle":"https://pith.science/pith/XHSYMPLYVVTR33HE7INTSYXPKZ/bundle.json","state":"https://pith.science/pith/XHSYMPLYVVTR33HE7INTSYXPKZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XHSYMPLYVVTR33HE7INTSYXPKZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XHSYMPLYVVTR33HE7INTSYXPKZ","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":"82ebc1026c65885c0c841d8688453097f80095d6cd0349eceb815e8071c6a0e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T03:35:01Z","title_canon_sha256":"7974260b7d5318cd513d2e245b98fbe739908f9c07682e9bfe9044b1afc1e101"},"schema_version":"1.0","source":{"id":"2110.09712","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.09712","created_at":"2026-07-05T05:10:35Z"},{"alias_kind":"arxiv_version","alias_value":"2110.09712v6","created_at":"2026-07-05T05:10:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09712","created_at":"2026-07-05T05:10:35Z"},{"alias_kind":"pith_short_12","alias_value":"XHSYMPLYVVTR","created_at":"2026-07-05T05:10:35Z"},{"alias_kind":"pith_short_16","alias_value":"XHSYMPLYVVTR33HE","created_at":"2026-07-05T05:10:35Z"},{"alias_kind":"pith_short_8","alias_value":"XHSYMPLY","created_at":"2026-07-05T05:10:35Z"}],"graph_snapshots":[{"event_id":"sha256:1eb98f94601aaaf41611a8e1447e637263e322c7e1636b0651ce54771600ecdd","target":"graph","created_at":"2026-07-05T05:10:35Z","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/2110.09712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-free deep reinforcement learning (RL) has been successfully applied to challenging continuous control domains. However, poor sample efficiency prevents these methods from being widely used in real-world domains. This paper introduces a novel model-free algorithm, Realistic Actor-Critic(RAC), which can be incorporated with any off-policy RL algorithms to improve sample efficiency. RAC employs Universal Value Function Approximators (UVFA) to simultaneously learn a policy family with the same neural network, each with different trade-offs between underestimation and overestimation. To learn","authors_text":"Gang Wang, Qinyun Tang, Sicen Li, Xinmeng Ma, Yiming Pang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T03:35:01Z","title":"Balancing Value Underestimation and Overestimation with Realistic Actor-Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09712","kind":"arxiv","version":6},"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:e119f09e51838083bb6eb8aae9e91b86fc7d4d0d80c94ecf54364e0b3909ac20","target":"record","created_at":"2026-07-05T05:10:35Z","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":"82ebc1026c65885c0c841d8688453097f80095d6cd0349eceb815e8071c6a0e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T03:35:01Z","title_canon_sha256":"7974260b7d5318cd513d2e245b98fbe739908f9c07682e9bfe9044b1afc1e101"},"schema_version":"1.0","source":{"id":"2110.09712","kind":"arxiv","version":6}},"canonical_sha256":"b9e5863d78ad671dece4fa1b3962ef566c20dba285175d514b54bd98616c3052","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9e5863d78ad671dece4fa1b3962ef566c20dba285175d514b54bd98616c3052","first_computed_at":"2026-07-05T05:10:35.093442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:35.093442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wkVxiOdGjtzG7NyTmgtYU8vlCHioD0aAsaHC1/qRUzUbr0MhWG+32zPQVTWfE/2mHK3pUYKKJVIQvDsneqDFDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:35.093886Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.09712","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e119f09e51838083bb6eb8aae9e91b86fc7d4d0d80c94ecf54364e0b3909ac20","sha256:1eb98f94601aaaf41611a8e1447e637263e322c7e1636b0651ce54771600ecdd"],"state_sha256":"0e853b3678aee474a3a8a8b5b8a757eede344f35ac78e3237073e8f17e6861c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LoHc5BMrXIUPULl223SBkGUkjh37ZYEHMagRDpO5+n5Kj52g4WZV/EnSwsIMJ8lMNxMmEz7CvKlq7dyQjEGbDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T10:09:47.020785Z","bundle_sha256":"0dc4581eb4060689ddb6ce336b7dfc0584793e6239177bbb7e837e53664a27dc"}}