{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HV6QLK3BDMYZ3Y72CH7AKDMXUD","short_pith_number":"pith:HV6QLK3B","canonical_record":{"source":{"id":"1906.08387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T22:46:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"28f4feed064d9cb5d19a0e5954b300091eb1b711c452db57f8f818fff6274337","abstract_canon_sha256":"972f553f46aa390f1cca9235a273160b1b755fc5adf136e3951f7f459998ed2b"},"schema_version":"1.0"},"canonical_sha256":"3d7d05ab611b319de3fa11fe050d97a0d8d0db36a2dc73ef941a94ccf542bfe0","source":{"kind":"arxiv","id":"1906.08387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08387","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08387v1","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08387","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"HV6QLK3BDMYZ","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HV6QLK3BDMYZ3Y72","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HV6QLK3B","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HV6QLK3BDMYZ3Y72CH7AKDMXUD","target":"record","payload":{"canonical_record":{"source":{"id":"1906.08387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T22:46:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"28f4feed064d9cb5d19a0e5954b300091eb1b711c452db57f8f818fff6274337","abstract_canon_sha256":"972f553f46aa390f1cca9235a273160b1b755fc5adf136e3951f7f459998ed2b"},"schema_version":"1.0"},"canonical_sha256":"3d7d05ab611b319de3fa11fe050d97a0d8d0db36a2dc73ef941a94ccf542bfe0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:52.616891Z","signature_b64":"EaVcksGu/+0P1B0Robxk2u9Ve6xE1mqNNaRJFR7kyq3Cq3oyivxNkgrIY+ok3NpcVEhcrcxiaCgr5B96X07iDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d7d05ab611b319de3fa11fe050d97a0d8d0db36a2dc73ef941a94ccf542bfe0","last_reissued_at":"2026-05-17T23:42:52.616396Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:52.616396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.08387","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":"2026-05-17T23:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MJwwHSx+axWvYCNqnrNxpuh+lWWCxzNiBc8SfAf+nSROrVSTxLvn2lMLQvw/Tab9/LgmC8pNA9P7U7X8yMftAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T20:12:01.797274Z"},"content_sha256":"cfe358f6c0eb44c027c719f9264bb8f84388f294d58a5bc5c68bae28c239f7e9","schema_version":"1.0","event_id":"sha256:cfe358f6c0eb44c027c719f9264bb8f84388f294d58a5bc5c68bae28c239f7e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HV6QLK3BDMYZ3Y72CH7AKDMXUD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Experience Replay Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daochen Zha, Kaixiong Zhou, Kwei-Herng Lai, Xia Hu","submitted_at":"2019-06-19T22:46:39Z","abstract_excerpt":"Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences uniformly or utilize a rule-based replay strategy, which may be sub-optimal. In this work, we consider learning a replay policy to optimize the cumulative reward. Replay learning is challenging because the replay memory is noisy and large, and the cumulative reward is unstable. To address these issues, we propose a novel experience replay optimization (ERO) framework which alte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08387","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":"2026-05-17T23:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mUL3Ba1vS87YYExjkCym7sh6llOdYwZ0EZ66hce/ix58iCUGVIw4FZTEk6t17Unl+ZT7VIw+pVuI1rq3sjIOBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T20:12:01.797933Z"},"content_sha256":"bc32c5163a37dd108843bfe78e2f9c9a6d4e4da3d3eba6730d5f5a9197781377","schema_version":"1.0","event_id":"sha256:bc32c5163a37dd108843bfe78e2f9c9a6d4e4da3d3eba6730d5f5a9197781377"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HV6QLK3BDMYZ3Y72CH7AKDMXUD/bundle.json","state_url":"https://pith.science/pith/HV6QLK3BDMYZ3Y72CH7AKDMXUD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HV6QLK3BDMYZ3Y72CH7AKDMXUD/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":"2026-05-18T20:12:01Z","links":{"resolver":"https://pith.science/pith/HV6QLK3BDMYZ3Y72CH7AKDMXUD","bundle":"https://pith.science/pith/HV6QLK3BDMYZ3Y72CH7AKDMXUD/bundle.json","state":"https://pith.science/pith/HV6QLK3BDMYZ3Y72CH7AKDMXUD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HV6QLK3BDMYZ3Y72CH7AKDMXUD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HV6QLK3BDMYZ3Y72CH7AKDMXUD","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":"972f553f46aa390f1cca9235a273160b1b755fc5adf136e3951f7f459998ed2b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T22:46:39Z","title_canon_sha256":"28f4feed064d9cb5d19a0e5954b300091eb1b711c452db57f8f818fff6274337"},"schema_version":"1.0","source":{"id":"1906.08387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08387","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08387v1","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08387","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"HV6QLK3BDMYZ","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HV6QLK3BDMYZ3Y72","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HV6QLK3B","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:bc32c5163a37dd108843bfe78e2f9c9a6d4e4da3d3eba6730d5f5a9197781377","target":"graph","created_at":"2026-05-17T23:42:52Z","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":"Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences uniformly or utilize a rule-based replay strategy, which may be sub-optimal. In this work, we consider learning a replay policy to optimize the cumulative reward. Replay learning is challenging because the replay memory is noisy and large, and the cumulative reward is unstable. To address these issues, we propose a novel experience replay optimization (ERO) framework which alte","authors_text":"Daochen Zha, Kaixiong Zhou, Kwei-Herng Lai, Xia Hu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T22:46:39Z","title":"Experience Replay Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08387","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:cfe358f6c0eb44c027c719f9264bb8f84388f294d58a5bc5c68bae28c239f7e9","target":"record","created_at":"2026-05-17T23:42:52Z","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":"972f553f46aa390f1cca9235a273160b1b755fc5adf136e3951f7f459998ed2b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T22:46:39Z","title_canon_sha256":"28f4feed064d9cb5d19a0e5954b300091eb1b711c452db57f8f818fff6274337"},"schema_version":"1.0","source":{"id":"1906.08387","kind":"arxiv","version":1}},"canonical_sha256":"3d7d05ab611b319de3fa11fe050d97a0d8d0db36a2dc73ef941a94ccf542bfe0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d7d05ab611b319de3fa11fe050d97a0d8d0db36a2dc73ef941a94ccf542bfe0","first_computed_at":"2026-05-17T23:42:52.616396Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:52.616396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EaVcksGu/+0P1B0Robxk2u9Ve6xE1mqNNaRJFR7kyq3Cq3oyivxNkgrIY+ok3NpcVEhcrcxiaCgr5B96X07iDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:52.616891Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.08387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfe358f6c0eb44c027c719f9264bb8f84388f294d58a5bc5c68bae28c239f7e9","sha256:bc32c5163a37dd108843bfe78e2f9c9a6d4e4da3d3eba6730d5f5a9197781377"],"state_sha256":"ea97b558794aa001c6ceeee4999860203a28ea3129b5f5d8a31f3bb1cc2341a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yryE8YEoefT1RQv7waI+szVMcq27BPKGFr7ZvRt/JtRPtJkzFlHiKE8uP6Y0Ihc+QeNr5fE3SdzUUnhgBtilBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T20:12:01.799483Z","bundle_sha256":"2502c03573a93aa652633bc4ca598479ca5ac14661dbfcfcc10c7dd283a38197"}}