{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OEGYMDXM76RMVPB326WQO4L3GC","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":"f18d67850937aa0d5b6c99a71fe0e0a3c777c28c0efc280d5116bfed8971545d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-07T15:01:20Z","title_canon_sha256":"52a9b6d1e5a710006b99e8ae41e30cb3d2a50d0adf697744ec0c0bea6c568cc7"},"schema_version":"1.0","source":{"id":"2002.02829","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.02829","created_at":"2026-07-05T00:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2002.02829v1","created_at":"2026-07-05T00:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02829","created_at":"2026-07-05T00:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"OEGYMDXM76RM","created_at":"2026-07-05T00:38:59Z"},{"alias_kind":"pith_short_16","alias_value":"OEGYMDXM76RMVPB3","created_at":"2026-07-05T00:38:59Z"},{"alias_kind":"pith_short_8","alias_value":"OEGYMDXM","created_at":"2026-07-05T00:38:59Z"}],"graph_snapshots":[{"event_id":"sha256:76d9bd039aed2eed6453960fa1607eca5001bd4f2d8066f23ed3b9b723442b7e","target":"graph","created_at":"2026-07-05T00:38:59Z","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/2002.02829/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The optimal policy of a reinforcement learning problem is often discontinuous and non-smooth. I.e., for two states with similar representations, their optimal policies can be significantly different. In this case, representing the entire policy with a function approximator (FA) with shared parameters for all states maybe not desirable, as the generalization ability of parameters sharing makes representing discontinuous, non-smooth policies difficult. A common way to solve this problem, known as Mixture-of-Experts, is to represent the policy as the weighted sum of multiple components, where dif","authors_text":"Chenglong Fu, Dongyu Li, Haoyong Yu, Kuangen Zhang, Yi Wan, Zhimin Hou","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-07T15:01:20Z","title":"Off-policy Maximum Entropy Reinforcement Learning : Soft Actor-Critic with Advantage Weighted Mixture Policy(SAC-AWMP)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02829","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:b57e4ed79d09bf5959f81318778f0e006776e665843e560f7b2664a3eb51acb5","target":"record","created_at":"2026-07-05T00:38:59Z","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":"f18d67850937aa0d5b6c99a71fe0e0a3c777c28c0efc280d5116bfed8971545d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-07T15:01:20Z","title_canon_sha256":"52a9b6d1e5a710006b99e8ae41e30cb3d2a50d0adf697744ec0c0bea6c568cc7"},"schema_version":"1.0","source":{"id":"2002.02829","kind":"arxiv","version":1}},"canonical_sha256":"710d860eecffa2cabc3bd7ad07717b30b3ab70db9b4272d958adff96a27e643a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"710d860eecffa2cabc3bd7ad07717b30b3ab70db9b4272d958adff96a27e643a","first_computed_at":"2026-07-05T00:38:59.719437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:38:59.719437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f+rXplZp5sKKX//PK/YdEO1wP0MBX7rtyy5294uLjxfAVm7hw+i+deQ1jqhLGROEJFXf4LRTfRxz0PGC4+GdCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:38:59.719858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.02829","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b57e4ed79d09bf5959f81318778f0e006776e665843e560f7b2664a3eb51acb5","sha256:76d9bd039aed2eed6453960fa1607eca5001bd4f2d8066f23ed3b9b723442b7e"],"state_sha256":"e3692c3643ea7e8d1d956f47acb84dd664398b66e9373f6d7409d2309cb52d50"}