{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7XDEG5DCEVEL64M5AHII6EPOMW","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":"c626926c9bee6724b75001f2a80d723b91d9f1af79b54e9c76e0951a8b40bfe7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-03T20:26:50Z","title_canon_sha256":"fdfc6cad32a26d7896e8dcfd2f092df26058910645e36fa8a0c869c2ed118462"},"schema_version":"1.0","source":{"id":"2007.01932","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.01932","created_at":"2026-07-05T01:23:36Z"},{"alias_kind":"arxiv_version","alias_value":"2007.01932v2","created_at":"2026-07-05T01:23:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01932","created_at":"2026-07-05T01:23:36Z"},{"alias_kind":"pith_short_12","alias_value":"7XDEG5DCEVEL","created_at":"2026-07-05T01:23:36Z"},{"alias_kind":"pith_short_16","alias_value":"7XDEG5DCEVEL64M5","created_at":"2026-07-05T01:23:36Z"},{"alias_kind":"pith_short_8","alias_value":"7XDEG5DC","created_at":"2026-07-05T01:23:36Z"}],"graph_snapshots":[{"event_id":"sha256:acbccb2b21e78987508fe50bfa7e5b3c56b39bea2198284d29e1e7de2409b15c","target":"graph","created_at":"2026-07-05T01:23:36Z","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/2007.01932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploration-exploitation dilemma has long been a crucial issue in reinforcement learning. In this paper, we propose a new approach to automatically balance between these two. Our method is built upon the Soft Actor-Critic (SAC) algorithm, which uses an \"entropy temperature\" that balances the original task reward and the policy entropy, and hence controls the trade-off between exploitation and exploration. It is empirically shown that SAC is very sensitive to this hyperparameter, and the follow-up work (SAC-v2), which uses constrained optimization for automatic adjustment, has some limitations.","authors_text":"Tianwei Ni, Yufei Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-03T20:26:50Z","title":"Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01932","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":"sha256:75572cf87d730f7346e4f2fabc62e7cbd71968f10c9cbc3ad6c0636516f43821","target":"record","created_at":"2026-07-05T01:23:36Z","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":"c626926c9bee6724b75001f2a80d723b91d9f1af79b54e9c76e0951a8b40bfe7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-03T20:26:50Z","title_canon_sha256":"fdfc6cad32a26d7896e8dcfd2f092df26058910645e36fa8a0c869c2ed118462"},"schema_version":"1.0","source":{"id":"2007.01932","kind":"arxiv","version":2}},"canonical_sha256":"fdc64374622548bf719d01d08f11ee65b05f546c3890e825d0f98cb9541eb0d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdc64374622548bf719d01d08f11ee65b05f546c3890e825d0f98cb9541eb0d6","first_computed_at":"2026-07-05T01:23:36.712502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:23:36.712502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U5gCm8PohLdGjdw7HU8eT4J3BT4gqGNN3/FKJp57997Wmay1APFj4/a+QtcuOkZRadShc00zPejE339WBZWbCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:23:36.712993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.01932","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75572cf87d730f7346e4f2fabc62e7cbd71968f10c9cbc3ad6c0636516f43821","sha256:acbccb2b21e78987508fe50bfa7e5b3c56b39bea2198284d29e1e7de2409b15c"],"state_sha256":"4a5f6ee87b4de5128898d0945170e0b091ea8479e4b8a95ea6d6dd65640159bc"}