{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3BD7ZFVRGNIZGXQE3YLHPZAPRC","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":"2386364c1c03638d01708632d0d8a416b5fe2bb4ebf66df1ee35816af79aafe1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T16:20:46Z","title_canon_sha256":"e825700c02bd93cd21ec58767538b6f209675f6e97f16932ee505c48650a506a"},"schema_version":"1.0","source":{"id":"1909.11583","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11583","created_at":"2026-07-05T00:20:01Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11583v2","created_at":"2026-07-05T00:20:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11583","created_at":"2026-07-05T00:20:01Z"},{"alias_kind":"pith_short_12","alias_value":"3BD7ZFVRGNIZ","created_at":"2026-07-05T00:20:01Z"},{"alias_kind":"pith_short_16","alias_value":"3BD7ZFVRGNIZGXQE","created_at":"2026-07-05T00:20:01Z"},{"alias_kind":"pith_short_8","alias_value":"3BD7ZFVR","created_at":"2026-07-05T00:20:01Z"}],"graph_snapshots":[{"event_id":"sha256:4494ceafeb3d4627f1fc99802f0c30741058d75f4998b752df75d68b9c9cf28e","target":"graph","created_at":"2026-07-05T00:20:01Z","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/1909.11583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the combination of actor-critic reinforcement learning algorithms with uniform large-scale experience replay and propose solutions for two challenges: (a) efficient actor-critic learning with experience replay (b) stability of off-policy learning where agents learn from other agents behaviour. We employ those insights to accelerate hyper-parameter sweeps in which all participating agents run concurrently and share their experience via a common replay module. To this end we analyze the bias-variance tradeoffs in V-trace, a form of importance sampling for actor-critic methods. Bas","authors_text":"Karen Simonyan, Matteo Hessel, Simon Schmitt","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T16:20:46Z","title":"Off-Policy Actor-Critic with Shared Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11583","kind":"arxiv","version":2},"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":"sha256:3aa3076f92293c8d00e862c35d7c2e5de2caa891b498f89c75db2b18b505eca3","target":"record","created_at":"2026-07-05T00:20:01Z","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":"2386364c1c03638d01708632d0d8a416b5fe2bb4ebf66df1ee35816af79aafe1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T16:20:46Z","title_canon_sha256":"e825700c02bd93cd21ec58767538b6f209675f6e97f16932ee505c48650a506a"},"schema_version":"1.0","source":{"id":"1909.11583","kind":"arxiv","version":2}},"canonical_sha256":"d847fc96b13351935e04de1677e40f88a3c3351ca8329d411fcbbc0798131e93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d847fc96b13351935e04de1677e40f88a3c3351ca8329d411fcbbc0798131e93","first_computed_at":"2026-07-05T00:20:01.869510Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:20:01.869510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"loS5SBY/6ecII5MJqzyi6JtIUyHMOPIMM1v9LZK701rBlnji6bRudZW3vM0lb5bQwQS7Z9F9cdCkTNZb4KXuAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:20:01.870043Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.11583","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3aa3076f92293c8d00e862c35d7c2e5de2caa891b498f89c75db2b18b505eca3","sha256:4494ceafeb3d4627f1fc99802f0c30741058d75f4998b752df75d68b9c9cf28e"],"state_sha256":"eecd43cbbc8aa27c21ad683c07feb32f4b175c9aded8bc991d63aa93aa3a3ecf"}