{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:Q6O7JZUZNLAQQG4MP75MNV7PLR","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":"ba6d7c04e3dbdf27a69ddd435ee39b58d638de7bf67a8243295d200d2dd4d470","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-16T08:11:08Z","title_canon_sha256":"2735e30b1df01b87e2a8aaed5288373d7c2a5bbeefa6bb4d257b23a9548ec868"},"schema_version":"1.0","source":{"id":"1910.07207","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.07207","created_at":"2026-07-05T00:13:04Z"},{"alias_kind":"arxiv_version","alias_value":"1910.07207v2","created_at":"2026-07-05T00:13:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.07207","created_at":"2026-07-05T00:13:04Z"},{"alias_kind":"pith_short_12","alias_value":"Q6O7JZUZNLAQ","created_at":"2026-07-05T00:13:04Z"},{"alias_kind":"pith_short_16","alias_value":"Q6O7JZUZNLAQQG4M","created_at":"2026-07-05T00:13:04Z"},{"alias_kind":"pith_short_8","alias_value":"Q6O7JZUZ","created_at":"2026-07-05T00:13:04Z"}],"graph_snapshots":[{"event_id":"sha256:54cdec5db9d95b642940e52b330e201841df4a434b1eb141a1e46c057c6ba9d3","target":"graph","created_at":"2026-07-05T00:13:04Z","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/1910.07207/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Soft Actor-Critic is a state-of-the-art reinforcement learning algorithm for continuous action settings that is not applicable to discrete action settings. Many important settings involve discrete actions, however, and so here we derive an alternative version of the Soft Actor-Critic algorithm that is applicable to discrete action settings. We then show that, even without any hyperparameter tuning, it is competitive with the tuned model-free state-of-the-art on a selection of games from the Atari suite.","authors_text":"Petros Christodoulou","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-16T08:11:08Z","title":"Soft Actor-Critic for Discrete Action Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.07207","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:e4795f174d36f5799c7095cb78c798ae2a8561f5b862251ca4ffd246eeb76859","target":"record","created_at":"2026-07-05T00:13:04Z","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":"ba6d7c04e3dbdf27a69ddd435ee39b58d638de7bf67a8243295d200d2dd4d470","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-16T08:11:08Z","title_canon_sha256":"2735e30b1df01b87e2a8aaed5288373d7c2a5bbeefa6bb4d257b23a9548ec868"},"schema_version":"1.0","source":{"id":"1910.07207","kind":"arxiv","version":2}},"canonical_sha256":"879df4e6996ac1081b8c7ffac6d7ef5c6ab2f51a9ead519c26046745f5cf40f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"879df4e6996ac1081b8c7ffac6d7ef5c6ab2f51a9ead519c26046745f5cf40f2","first_computed_at":"2026-07-05T00:13:04.937247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:13:04.937247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DwuU9TC2D2tMFPFBBVJeK5U10nNMZvk9Ya19Q5kx7VWp21xfcsY9Fj3X/DZ+fyZaT4n23TF0gsXcsW9Bi70iBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:13:04.937639Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.07207","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4795f174d36f5799c7095cb78c798ae2a8561f5b862251ca4ffd246eeb76859","sha256:54cdec5db9d95b642940e52b330e201841df4a434b1eb141a1e46c057c6ba9d3"],"state_sha256":"63830c47107e667bd1417bf2aba91933c79ced8bd84a0eb6bee0162862b48a55"}