{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XYV632LGBWITCLRPIVX2XM3PZ2","short_pith_number":"pith:XYV632LG","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"},"canonical_sha256":"be2bede9660d91312e2f456fabb36fceb89df294ffbaecaa8716de52f1cb08bd","source":{"kind":"arxiv","id":"1906.04009","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04009","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04009v1","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04009","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"XYV632LGBWIT","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XYV632LGBWITCLRP","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XYV632LG","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XYV632LGBWITCLRPIVX2XM3PZ2","target":"record","payload":{"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"},"canonical_sha256":"be2bede9660d91312e2f456fabb36fceb89df294ffbaecaa8716de52f1cb08bd","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"},"source_kind":"arxiv","source_id":"1906.04009","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":"2026-05-17T23:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ER9kPuJCZStuIpel7ZiVWG6YSHttB4P5WHbHjYJ5gRSamX/Z5jXU6YLRJ4jYqxouLw9zobQPOgwnX/PJ8hOBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:17:09.013017Z"},"content_sha256":"f0881b2bd4be2ee1f0736a78d014e8ba8d9c495fb023e37b92e8f283021fd37b","schema_version":"1.0","event_id":"sha256:f0881b2bd4be2ee1f0736a78d014e8ba8d9c495fb023e37b92e8f283021fd37b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XYV632LGBWITCLRPIVX2XM3PZ2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vjemkfvaPflDUzdOyjY9gjOvToGqc7sQVZLEw1eMy3G9LYzEOzJihtpEaTSB4KZwpnyLTokUNnSVAttcGJc2BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:17:09.013717Z"},"content_sha256":"08cf40673a7a928bf32079529568846749341affe06cc8e4e0ec3d41d0b1a8e6","schema_version":"1.0","event_id":"sha256:08cf40673a7a928bf32079529568846749341affe06cc8e4e0ec3d41d0b1a8e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2/bundle.json","state_url":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XYV632LGBWITCLRPIVX2XM3PZ2/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":"2026-05-31T18:17:09Z","links":{"resolver":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2","bundle":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2/bundle.json","state":"https://pith.science/pith/XYV632LGBWITCLRPIVX2XM3PZ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XYV632LGBWITCLRPIVX2XM3PZ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XYV632LGBWITCLRPIVX2XM3PZ2","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":"233f3abe2832d42df54366a59136656c4d1297c387fb90651fb82c915e618483","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T14:27:13Z","title_canon_sha256":"255dcfd1a21e8dc85b3494ccf5ec6212c3eb54c0d4cde9ab251c9cc54ffcf82e"},"schema_version":"1.0","source":{"id":"1906.04009","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04009","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04009v1","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04009","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"XYV632LGBWIT","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XYV632LGBWITCLRP","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XYV632LG","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:08cf40673a7a928bf32079529568846749341affe06cc8e4e0ec3d41d0b1a8e6","target":"graph","created_at":"2026-05-17T23:43:44Z","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":"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","authors_text":"Che Wang, Keith Ross","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T14:27:13Z","title":"Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04009","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:f0881b2bd4be2ee1f0736a78d014e8ba8d9c495fb023e37b92e8f283021fd37b","target":"record","created_at":"2026-05-17T23:43:44Z","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":"233f3abe2832d42df54366a59136656c4d1297c387fb90651fb82c915e618483","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T14:27:13Z","title_canon_sha256":"255dcfd1a21e8dc85b3494ccf5ec6212c3eb54c0d4cde9ab251c9cc54ffcf82e"},"schema_version":"1.0","source":{"id":"1906.04009","kind":"arxiv","version":1}},"canonical_sha256":"be2bede9660d91312e2f456fabb36fceb89df294ffbaecaa8716de52f1cb08bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be2bede9660d91312e2f456fabb36fceb89df294ffbaecaa8716de52f1cb08bd","first_computed_at":"2026-05-17T23:43:44.199993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:44.199993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SG887Hlc9AlK2uVJZrS37Wm270sWCUH1VJgkoYJyZN5FtsWbjPiJq5RBbe7qeP7Yc+kYLjfG30lBCpkOMcCIDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:44.200486Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.04009","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0881b2bd4be2ee1f0736a78d014e8ba8d9c495fb023e37b92e8f283021fd37b","sha256:08cf40673a7a928bf32079529568846749341affe06cc8e4e0ec3d41d0b1a8e6"],"state_sha256":"cb185eca0c649732236df3a926e49b02c844a4f75f07e82ad69c56e9ee280a50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ycb4JLSvI76EywoC8bRcD7sCYWl/eZ7LNKO/k6HzQt0U6tt3h21YyryE6CyyzNynv4iGr4b82sVOHRUExvbYBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T18:17:09.017709Z","bundle_sha256":"05bd8e7790f4dc273adf628068a400c79969433371da438616386823797ff468"}}