{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XYV632LGBWITCLRPIVX2XM3PZ2","short_pith_number":"pith:XYV632LG","schema_version":"1.0","canonical_sha256":"be2bede9660d91312e2f456fabb36fceb89df294ffbaecaa8716de52f1cb08bd","source":{"kind":"arxiv","id":"1906.04009","version":1},"attestation_state":"computed","paper":{"title":"Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Che Wang, Keith Ross","submitted_at":"2019-06-10T14:27:13Z","abstract_excerpt":"Soft Actor-Critic (SAC) is an off-policy actor-critic deep reinforcement learning (DRL) algorithm based on maximum entropy reinforcement learning. By combining off-policy updates with an actor-critic formulation, SAC achieves state-of-the-art performance on a range of continuous-action benchmark tasks, outperforming prior on-policy and off-policy methods. The off-policy method employed by SAC samples data uniformly from past experience when performing parameter updates. We propose Emphasizing Recent Experience (ERE), a simple but powerful off-policy sampling technique, which emphasizes recentl"},"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":"1906.04009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T14:27:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"255dcfd1a21e8dc85b3494ccf5ec6212c3eb54c0d4cde9ab251c9cc54ffcf82e","abstract_canon_sha256":"233f3abe2832d42df54366a59136656c4d1297c387fb90651fb82c915e618483"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:44.200486Z","signature_b64":"SG887Hlc9AlK2uVJZrS37Wm270sWCUH1VJgkoYJyZN5FtsWbjPiJq5RBbe7qeP7Yc+kYLjfG30lBCpkOMcCIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be2bede9660d91312e2f456fabb36fceb89df294ffbaecaa8716de52f1cb08bd","last_reissued_at":"2026-05-17T23:43:44.199993Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:44.199993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Che Wang, Keith Ross","submitted_at":"2019-06-10T14:27:13Z","abstract_excerpt":"Soft Actor-Critic (SAC) is an off-policy actor-critic deep reinforcement learning (DRL) algorithm based on maximum entropy reinforcement learning. By combining off-policy updates with an actor-critic formulation, SAC achieves state-of-the-art performance on a range of continuous-action benchmark tasks, outperforming prior on-policy and off-policy methods. The off-policy method employed by SAC samples data uniformly from past experience when performing parameter updates. We propose Emphasizing Recent Experience (ERE), a simple but powerful off-policy sampling technique, which emphasizes recentl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04009","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1906.04009","created_at":"2026-05-17T23:43:44.200061+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04009v1","created_at":"2026-05-17T23:43:44.200061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04009","created_at":"2026-05-17T23:43:44.200061+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYV632LGBWIT","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYV632LGBWITCLRP","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYV632LG","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.10236","citing_title":"When Does Non-Uniform Replay Matter in Reinforcement Learning?","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10236","citing_title":"When Does Non-Uniform Replay Matter in Reinforcement Learning?","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10236","citing_title":"When Does Non-Uniform Replay Matter in Reinforcement Learning?","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2","json":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2.json","graph_json":"https://pith.science/api/pith-number/XYV632LGBWITCLRPIVX2XM3PZ2/graph.json","events_json":"https://pith.science/api/pith-number/XYV632LGBWITCLRPIVX2XM3PZ2/events.json","paper":"https://pith.science/paper/XYV632LG"},"agent_actions":{"view_html":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2","download_json":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2.json","view_paper":"https://pith.science/paper/XYV632LG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04009&json=true","fetch_graph":"https://pith.science/api/pith-number/XYV632LGBWITCLRPIVX2XM3PZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/XYV632LGBWITCLRPIVX2XM3PZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2/action/storage_attestation","attest_author":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2/action/author_attestation","sign_citation":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2/action/citation_signature","submit_replication":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2/action/replication_record"}},"created_at":"2026-05-17T23:43:44.200061+00:00","updated_at":"2026-05-17T23:43:44.200061+00:00"}