{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AKCHYBNVPXXYIYDGVTGV4ZALUG","short_pith_number":"pith:AKCHYBNV","canonical_record":{"source":{"id":"2408.01972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-04T09:26:00Z","cross_cats_sorted":[],"title_canon_sha256":"d3692aa2703b0bb5d4d85811677a24ec98ca97553f38a7a715052a0c49ec1b56","abstract_canon_sha256":"81e7dde211b97b0fa85f28c025a74ad843f59ffcee407dec2287854c4f5200fd"},"schema_version":"1.0"},"canonical_sha256":"02847c05b57def846066accd5e640ba1a886ced0efda8efab09c911253a2da5e","source":{"kind":"arxiv","id":"2408.01972","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01972","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01972v1","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01972","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"pith_short_12","alias_value":"AKCHYBNVPXXY","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"pith_short_16","alias_value":"AKCHYBNVPXXYIYDG","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"pith_short_8","alias_value":"AKCHYBNV","created_at":"2026-07-05T08:52:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AKCHYBNVPXXYIYDGVTGV4ZALUG","target":"record","payload":{"canonical_record":{"source":{"id":"2408.01972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-04T09:26:00Z","cross_cats_sorted":[],"title_canon_sha256":"d3692aa2703b0bb5d4d85811677a24ec98ca97553f38a7a715052a0c49ec1b56","abstract_canon_sha256":"81e7dde211b97b0fa85f28c025a74ad843f59ffcee407dec2287854c4f5200fd"},"schema_version":"1.0"},"canonical_sha256":"02847c05b57def846066accd5e640ba1a886ced0efda8efab09c911253a2da5e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:05.660913Z","signature_b64":"D9r3fZlDKYMMiCnaO81YXUVkJsYT0fI0zJeIooIgxE/d+KwAbAnGIKXtv4o6tHl3w5SbIhprNIkWcyy2lDG/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02847c05b57def846066accd5e640ba1a886ced0efda8efab09c911253a2da5e","last_reissued_at":"2026-07-05T08:52:05.660518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:05.660518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.01972","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":"2026-07-05T08:52:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4gyhMq/r1NiW9xolQxr9zJNR11UnHbHo5gyrX+ug2+3TLXWS8OnxKliQkuVks0StMrDhmfqWsUORiGWo/XGTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:13:22.807507Z"},"content_sha256":"006961f1c058f3be230c1d0ee382b46c50d08d4fde567a015aba43c958b3a97c","schema_version":"1.0","event_id":"sha256:006961f1c058f3be230c1d0ee382b46c50d08d4fde567a015aba43c958b3a97c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AKCHYBNVPXXYIYDGVTGV4ZALUG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Isao Ono, Yukinari Hisaki","submitted_at":"2024-08-04T09:26:00Z","abstract_excerpt":"In this paper, we propose an off-policy deep reinforcement learning (DRL) method utilizing the average reward criterion. While most existing DRL methods employ the discounted reward criterion, this can potentially lead to a discrepancy between the training objective and performance metrics in continuing tasks, making the average reward criterion a recommended alternative. We introduce RVI-SAC, an extension of the state-of-the-art off-policy DRL method, Soft Actor-Critic (SAC), to the average reward criterion. Our proposal consists of (1) Critic updates based on RVI Q-learning, (2) Actor update"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01972","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/2408.01972/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":"2026-07-05T08:52:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q5d+Rdq/l4DO/b7Fs3aiKCt0dhgbg0Rd8axgoIU1ttC1kwz/r5bP44NQ2W81DkkLnYigy2s4Yx8n5rcmXNfJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:13:22.808021Z"},"content_sha256":"95caae0724f6cf9b5cf56f5ab688501081e307d1127253e6d970cb3791774c57","schema_version":"1.0","event_id":"sha256:95caae0724f6cf9b5cf56f5ab688501081e307d1127253e6d970cb3791774c57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AKCHYBNVPXXYIYDGVTGV4ZALUG/bundle.json","state_url":"https://pith.science/pith/AKCHYBNVPXXYIYDGVTGV4ZALUG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AKCHYBNVPXXYIYDGVTGV4ZALUG/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":"2026-08-22T00:13:22Z","links":{"resolver":"https://pith.science/pith/AKCHYBNVPXXYIYDGVTGV4ZALUG","bundle":"https://pith.science/pith/AKCHYBNVPXXYIYDGVTGV4ZALUG/bundle.json","state":"https://pith.science/pith/AKCHYBNVPXXYIYDGVTGV4ZALUG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AKCHYBNVPXXYIYDGVTGV4ZALUG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AKCHYBNVPXXYIYDGVTGV4ZALUG","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":"81e7dde211b97b0fa85f28c025a74ad843f59ffcee407dec2287854c4f5200fd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-04T09:26:00Z","title_canon_sha256":"d3692aa2703b0bb5d4d85811677a24ec98ca97553f38a7a715052a0c49ec1b56"},"schema_version":"1.0","source":{"id":"2408.01972","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01972","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01972v1","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01972","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"pith_short_12","alias_value":"AKCHYBNVPXXY","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"pith_short_16","alias_value":"AKCHYBNVPXXYIYDG","created_at":"2026-07-05T08:52:05Z"},{"alias_kind":"pith_short_8","alias_value":"AKCHYBNV","created_at":"2026-07-05T08:52:05Z"}],"graph_snapshots":[{"event_id":"sha256:95caae0724f6cf9b5cf56f5ab688501081e307d1127253e6d970cb3791774c57","target":"graph","created_at":"2026-07-05T08:52:05Z","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/2408.01972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose an off-policy deep reinforcement learning (DRL) method utilizing the average reward criterion. While most existing DRL methods employ the discounted reward criterion, this can potentially lead to a discrepancy between the training objective and performance metrics in continuing tasks, making the average reward criterion a recommended alternative. We introduce RVI-SAC, an extension of the state-of-the-art off-policy DRL method, Soft Actor-Critic (SAC), to the average reward criterion. Our proposal consists of (1) Critic updates based on RVI Q-learning, (2) Actor update","authors_text":"Isao Ono, Yukinari Hisaki","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-04T09:26:00Z","title":"RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01972","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":"sha256:006961f1c058f3be230c1d0ee382b46c50d08d4fde567a015aba43c958b3a97c","target":"record","created_at":"2026-07-05T08:52:05Z","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":"81e7dde211b97b0fa85f28c025a74ad843f59ffcee407dec2287854c4f5200fd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-04T09:26:00Z","title_canon_sha256":"d3692aa2703b0bb5d4d85811677a24ec98ca97553f38a7a715052a0c49ec1b56"},"schema_version":"1.0","source":{"id":"2408.01972","kind":"arxiv","version":1}},"canonical_sha256":"02847c05b57def846066accd5e640ba1a886ced0efda8efab09c911253a2da5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02847c05b57def846066accd5e640ba1a886ced0efda8efab09c911253a2da5e","first_computed_at":"2026-07-05T08:52:05.660518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:05.660518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D9r3fZlDKYMMiCnaO81YXUVkJsYT0fI0zJeIooIgxE/d+KwAbAnGIKXtv4o6tHl3w5SbIhprNIkWcyy2lDG/CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:05.660913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.01972","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:006961f1c058f3be230c1d0ee382b46c50d08d4fde567a015aba43c958b3a97c","sha256:95caae0724f6cf9b5cf56f5ab688501081e307d1127253e6d970cb3791774c57"],"state_sha256":"102f697d2c697fbc041c7095f245e31c5458c94fc9e6aa19fb5102f389860c6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G43wIMDvkrsmfNyWnHusqNpZ771e/fkxLCc3PG41YmqtwnVdXwR4oIehbetdfElLbMxoKTkx9Jorz+qIIPLABA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T00:13:22.811868Z","bundle_sha256":"81f400c830abc9dd15336418c1364ee6c088d71a9d6bb9f15e1eae1b02e181a4"}}