{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3BD7ZFVRGNIZGXQE3YLHPZAPRC","short_pith_number":"pith:3BD7ZFVR","schema_version":"1.0","canonical_sha256":"d847fc96b13351935e04de1677e40f88a3c3351ca8329d411fcbbc0798131e93","source":{"kind":"arxiv","id":"1909.11583","version":2},"attestation_state":"computed","paper":{"title":"Off-Policy Actor-Critic with Shared Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Karen Simonyan, Matteo Hessel, Simon Schmitt","submitted_at":"2019-09-25T16:20:46Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1909.11583","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T16:20:46Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e825700c02bd93cd21ec58767538b6f209675f6e97f16932ee505c48650a506a","abstract_canon_sha256":"2386364c1c03638d01708632d0d8a416b5fe2bb4ebf66df1ee35816af79aafe1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:01.870043Z","signature_b64":"loS5SBY/6ecII5MJqzyi6JtIUyHMOPIMM1v9LZK701rBlnji6bRudZW3vM0lb5bQwQS7Z9F9cdCkTNZb4KXuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d847fc96b13351935e04de1677e40f88a3c3351ca8329d411fcbbc0798131e93","last_reissued_at":"2026-07-05T00:20:01.869510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:01.869510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Off-Policy Actor-Critic with Shared Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Karen Simonyan, Matteo Hessel, Simon Schmitt","submitted_at":"2019-09-25T16:20:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11583","kind":"arxiv","version":2},"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/1909.11583/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1909.11583","created_at":"2026-07-05T00:20:01.869590+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.11583v2","created_at":"2026-07-05T00:20:01.869590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11583","created_at":"2026-07-05T00:20:01.869590+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BD7ZFVRGNIZ","created_at":"2026-07-05T00:20:01.869590+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BD7ZFVRGNIZGXQE","created_at":"2026-07-05T00:20:01.869590+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BD7ZFVR","created_at":"2026-07-05T00:20:01.869590+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1911.08265","citing_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3BD7ZFVRGNIZGXQE3YLHPZAPRC","json":"https://pith.science/pith/3BD7ZFVRGNIZGXQE3YLHPZAPRC.json","graph_json":"https://pith.science/api/pith-number/3BD7ZFVRGNIZGXQE3YLHPZAPRC/graph.json","events_json":"https://pith.science/api/pith-number/3BD7ZFVRGNIZGXQE3YLHPZAPRC/events.json","paper":"https://pith.science/paper/3BD7ZFVR"},"agent_actions":{"view_html":"https://pith.science/pith/3BD7ZFVRGNIZGXQE3YLHPZAPRC","download_json":"https://pith.science/pith/3BD7ZFVRGNIZGXQE3YLHPZAPRC.json","view_paper":"https://pith.science/paper/3BD7ZFVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.11583&json=true","fetch_graph":"https://pith.science/api/pith-number/3BD7ZFVRGNIZGXQE3YLHPZAPRC/graph.json","fetch_events":"https://pith.science/api/pith-number/3BD7ZFVRGNIZGXQE3YLHPZAPRC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BD7ZFVRGNIZGXQE3YLHPZAPRC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BD7ZFVRGNIZGXQE3YLHPZAPRC/action/storage_attestation","attest_author":"https://pith.science/pith/3BD7ZFVRGNIZGXQE3YLHPZAPRC/action/author_attestation","sign_citation":"https://pith.science/pith/3BD7ZFVRGNIZGXQE3YLHPZAPRC/action/citation_signature","submit_replication":"https://pith.science/pith/3BD7ZFVRGNIZGXQE3YLHPZAPRC/action/replication_record"}},"created_at":"2026-07-05T00:20:01.869590+00:00","updated_at":"2026-07-05T00:20:01.869590+00:00"}