{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:43PCZZVEQUE7CZAVYAGRNV3VZF","short_pith_number":"pith:43PCZZVE","canonical_record":{"source":{"id":"1912.05328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-10T09:56:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b04455731f4fbd41f61692f92b805f709ab8ce16253160b049ef560e7bddff79","abstract_canon_sha256":"317e3c600866cc4a225e3c1c9aca33d09a34ee4b3d289c07f3bc52531ba4328f"},"schema_version":"1.0"},"canonical_sha256":"e6de2ce6a48509f16415c00d16d775c978e618c76a318c811d285b80b5236ea2","source":{"kind":"arxiv","id":"1912.05328","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05328","created_at":"2026-07-05T00:25:34Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05328v1","created_at":"2026-07-05T00:25:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05328","created_at":"2026-07-05T00:25:34Z"},{"alias_kind":"pith_short_12","alias_value":"43PCZZVEQUE7","created_at":"2026-07-05T00:25:34Z"},{"alias_kind":"pith_short_16","alias_value":"43PCZZVEQUE7CZAV","created_at":"2026-07-05T00:25:34Z"},{"alias_kind":"pith_short_8","alias_value":"43PCZZVE","created_at":"2026-07-05T00:25:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:43PCZZVEQUE7CZAVYAGRNV3VZF","target":"record","payload":{"canonical_record":{"source":{"id":"1912.05328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-10T09:56:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b04455731f4fbd41f61692f92b805f709ab8ce16253160b049ef560e7bddff79","abstract_canon_sha256":"317e3c600866cc4a225e3c1c9aca33d09a34ee4b3d289c07f3bc52531ba4328f"},"schema_version":"1.0"},"canonical_sha256":"e6de2ce6a48509f16415c00d16d775c978e618c76a318c811d285b80b5236ea2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:34.440302Z","signature_b64":"W8XvrhUCadfPzs+upMb3ArXOWCl/I+2y+xnx+elFYJ5yW7JRNlMp7267xH5mAHHKLbBBaBzr8Teqo6oquHvbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6de2ce6a48509f16415c00d16d775c978e618c76a318c811d285b80b5236ea2","last_reissued_at":"2026-07-05T00:25:34.439884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:34.439884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.05328","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":"2026-07-05T00:25:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zmCbHcLD0AulFNz8MEH9RNKqeSihixejV2oEIwWYZH5cfjUtOr52TNTow9/4qS6X7iZALtFJRCoA4vQO93E1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:06:26.544792Z"},"content_sha256":"8da40130653ff050be1f11a962b6f4c7e01cbd99ffb2d8c576d08294bb9c33da","schema_version":"1.0","event_id":"sha256:8da40130653ff050be1f11a962b6f4c7e01cbd99ffb2d8c576d08294bb9c33da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:43PCZZVEQUE7CZAVYAGRNV3VZF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient and Robust Reinforcement Learning with Uncertainty-based Value Expansion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Zhou, Fan Wang, Hao Tian, Hongsheng Zeng, Yunxiang Li","submitted_at":"2019-12-10T09:56:14Z","abstract_excerpt":"By integrating dynamics models into model-free reinforcement learning (RL) methods, model-based value expansion (MVE) algorithms have shown a significant advantage in sample efficiency as well as value estimation. However, these methods suffer from higher function approximation errors than model-free methods in stochastic environments due to a lack of modeling the environmental randomness. As a result, their performance lags behind the best model-free algorithms in some challenging scenarios. In this paper, we propose a novel Hybrid-RL method that builds on MVE, namely the Risk Averse Value Ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05328","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.05328/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":"2026-07-05T00:25:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c2Uhh2cG8BJeP+Dnc/VlYufvumES5cGJ2w9LPTwlwwR2/ZA0wItWg2sLDQOC3WSb9hPudYEo26ENQXnpWD3yBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:06:26.545164Z"},"content_sha256":"2809a4b89ded65f537371a6351369a00ca1e7f9bebcc6b0b188e753b650a0151","schema_version":"1.0","event_id":"sha256:2809a4b89ded65f537371a6351369a00ca1e7f9bebcc6b0b188e753b650a0151"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/43PCZZVEQUE7CZAVYAGRNV3VZF/bundle.json","state_url":"https://pith.science/pith/43PCZZVEQUE7CZAVYAGRNV3VZF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/43PCZZVEQUE7CZAVYAGRNV3VZF/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":"2026-07-07T10:06:26Z","links":{"resolver":"https://pith.science/pith/43PCZZVEQUE7CZAVYAGRNV3VZF","bundle":"https://pith.science/pith/43PCZZVEQUE7CZAVYAGRNV3VZF/bundle.json","state":"https://pith.science/pith/43PCZZVEQUE7CZAVYAGRNV3VZF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/43PCZZVEQUE7CZAVYAGRNV3VZF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:43PCZZVEQUE7CZAVYAGRNV3VZF","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":"317e3c600866cc4a225e3c1c9aca33d09a34ee4b3d289c07f3bc52531ba4328f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-10T09:56:14Z","title_canon_sha256":"b04455731f4fbd41f61692f92b805f709ab8ce16253160b049ef560e7bddff79"},"schema_version":"1.0","source":{"id":"1912.05328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05328","created_at":"2026-07-05T00:25:34Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05328v1","created_at":"2026-07-05T00:25:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05328","created_at":"2026-07-05T00:25:34Z"},{"alias_kind":"pith_short_12","alias_value":"43PCZZVEQUE7","created_at":"2026-07-05T00:25:34Z"},{"alias_kind":"pith_short_16","alias_value":"43PCZZVEQUE7CZAV","created_at":"2026-07-05T00:25:34Z"},{"alias_kind":"pith_short_8","alias_value":"43PCZZVE","created_at":"2026-07-05T00:25:34Z"}],"graph_snapshots":[{"event_id":"sha256:2809a4b89ded65f537371a6351369a00ca1e7f9bebcc6b0b188e753b650a0151","target":"graph","created_at":"2026-07-05T00:25:34Z","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/1912.05328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"By integrating dynamics models into model-free reinforcement learning (RL) methods, model-based value expansion (MVE) algorithms have shown a significant advantage in sample efficiency as well as value estimation. However, these methods suffer from higher function approximation errors than model-free methods in stochastic environments due to a lack of modeling the environmental randomness. As a result, their performance lags behind the best model-free algorithms in some challenging scenarios. In this paper, we propose a novel Hybrid-RL method that builds on MVE, namely the Risk Averse Value Ex","authors_text":"Bo Zhou, Fan Wang, Hao Tian, Hongsheng Zeng, Yunxiang Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-10T09:56:14Z","title":"Efficient and Robust Reinforcement Learning with Uncertainty-based Value Expansion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05328","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":"sha256:8da40130653ff050be1f11a962b6f4c7e01cbd99ffb2d8c576d08294bb9c33da","target":"record","created_at":"2026-07-05T00:25:34Z","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":"317e3c600866cc4a225e3c1c9aca33d09a34ee4b3d289c07f3bc52531ba4328f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-10T09:56:14Z","title_canon_sha256":"b04455731f4fbd41f61692f92b805f709ab8ce16253160b049ef560e7bddff79"},"schema_version":"1.0","source":{"id":"1912.05328","kind":"arxiv","version":1}},"canonical_sha256":"e6de2ce6a48509f16415c00d16d775c978e618c76a318c811d285b80b5236ea2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6de2ce6a48509f16415c00d16d775c978e618c76a318c811d285b80b5236ea2","first_computed_at":"2026-07-05T00:25:34.439884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:25:34.439884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W8XvrhUCadfPzs+upMb3ArXOWCl/I+2y+xnx+elFYJ5yW7JRNlMp7267xH5mAHHKLbBBaBzr8Teqo6oquHvbCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:25:34.440302Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.05328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8da40130653ff050be1f11a962b6f4c7e01cbd99ffb2d8c576d08294bb9c33da","sha256:2809a4b89ded65f537371a6351369a00ca1e7f9bebcc6b0b188e753b650a0151"],"state_sha256":"a7568b07e2a0db4fc15b761e16fdcc3199b4739eaa5e4437dd424cb3cf5f8585"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"97/Qbh8mTEsoodrUqdisUFb18jegvQkERiURRSyEurW8tUJF6sPz5eUE3jM4q+AtNp3sTatflpd+Xsrt9QZ3Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:06:26.547073Z","bundle_sha256":"fc8209043a258327bfb06476f974942c80d528ab5d18e0e0f4893c95c1914153"}}