{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4V2LNT7SASOTSVP6M472XC6HQL","short_pith_number":"pith:4V2LNT7S","canonical_record":{"source":{"id":"1912.01557","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-02T11:01:32Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5864412765c9ef1a5b91ee6a5b213e86f3b9f316c28248fcc942e3603b46ed5e","abstract_canon_sha256":"ed58542178b41b00b87daad2405696a67380acf7a135187a0be7269601309803"},"schema_version":"1.0"},"canonical_sha256":"e574b6cff2049d3955fe673fab8bc782de716159d37e0a6144fa9e896428901c","source":{"kind":"arxiv","id":"1912.01557","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.01557","created_at":"2026-07-05T01:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"1912.01557v3","created_at":"2026-07-05T01:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.01557","created_at":"2026-07-05T01:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"4V2LNT7SASOT","created_at":"2026-07-05T01:43:23Z"},{"alias_kind":"pith_short_16","alias_value":"4V2LNT7SASOTSVP6","created_at":"2026-07-05T01:43:23Z"},{"alias_kind":"pith_short_8","alias_value":"4V2LNT7S","created_at":"2026-07-05T01:43:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4V2LNT7SASOTSVP6M472XC6HQL","target":"record","payload":{"canonical_record":{"source":{"id":"1912.01557","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-02T11:01:32Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5864412765c9ef1a5b91ee6a5b213e86f3b9f316c28248fcc942e3603b46ed5e","abstract_canon_sha256":"ed58542178b41b00b87daad2405696a67380acf7a135187a0be7269601309803"},"schema_version":"1.0"},"canonical_sha256":"e574b6cff2049d3955fe673fab8bc782de716159d37e0a6144fa9e896428901c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:23.897806Z","signature_b64":"tEgzPfCOSrJUb+Fj/D3/k8JvLXqnoYp9mlle6AvSEGutFXFhC3c5MTXlT+CKRosMirlIqKaPJuT/GiX9SIQQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e574b6cff2049d3955fe673fab8bc782de716159d37e0a6144fa9e896428901c","last_reissued_at":"2026-07-05T01:43:23.897326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:23.897326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.01557","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:43:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NyzgJLrSVYhtVj6lEcROlNHmY8zPykPJHqiPeLy/GImS8RFXbjq4t5Ri3FgxGAvSeCb9Ttej1FxaTIpozb9SCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:05:43.905311Z"},"content_sha256":"2d69834b68eb82f50e1c7cc181534b88ce0bc6361a2bb606796cf50b2530f870","schema_version":"1.0","event_id":"sha256:2d69834b68eb82f50e1c7cc181534b88ce0bc6361a2bb606796cf50b2530f870"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4V2LNT7SASOTSVP6M472XC6HQL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Optimization Reinforcement Learning with Entropy Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jingbin Liu, Shuai Liu, Xinyang Gu","submitted_at":"2019-12-02T11:01:32Z","abstract_excerpt":"Entropy regularization is an important idea in reinforcement learning, with great success in recent algorithms like Soft Q Network (SQN) and Soft Actor-Critic (SAC1). In this work, we extend this idea into the on-policy realm. We propose the soft policy gradient theorem (SPGT) for on-policy maximum entropy reinforcement learning. With SPGT, a series of new policy optimization algorithms are derived, such as SPG, SA2C, SA3C, SDDPG, STRPO, SPPO, SIMPALA and so on. We find that SDDPG is equivalent to SAC1. For policy gradient, the policy network is often represented as a Gaussian distribution wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.01557","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.01557/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:43:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"skWK8GgnZe4biwlPN5oFu8fEnI6fgqs3jeX+1Nk83esY6546ict8NaEk21bbk2w+5HT9QIwA/vMru9W3gzxlDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:05:43.905706Z"},"content_sha256":"e0edf9749d195183500233a18700bdae0868deeb1cbe53b053eddd232d01b062","schema_version":"1.0","event_id":"sha256:e0edf9749d195183500233a18700bdae0868deeb1cbe53b053eddd232d01b062"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4V2LNT7SASOTSVP6M472XC6HQL/bundle.json","state_url":"https://pith.science/pith/4V2LNT7SASOTSVP6M472XC6HQL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4V2LNT7SASOTSVP6M472XC6HQL/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":"2026-07-09T05:05:43Z","links":{"resolver":"https://pith.science/pith/4V2LNT7SASOTSVP6M472XC6HQL","bundle":"https://pith.science/pith/4V2LNT7SASOTSVP6M472XC6HQL/bundle.json","state":"https://pith.science/pith/4V2LNT7SASOTSVP6M472XC6HQL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4V2LNT7SASOTSVP6M472XC6HQL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4V2LNT7SASOTSVP6M472XC6HQL","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":"ed58542178b41b00b87daad2405696a67380acf7a135187a0be7269601309803","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-02T11:01:32Z","title_canon_sha256":"5864412765c9ef1a5b91ee6a5b213e86f3b9f316c28248fcc942e3603b46ed5e"},"schema_version":"1.0","source":{"id":"1912.01557","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.01557","created_at":"2026-07-05T01:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"1912.01557v3","created_at":"2026-07-05T01:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.01557","created_at":"2026-07-05T01:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"4V2LNT7SASOT","created_at":"2026-07-05T01:43:23Z"},{"alias_kind":"pith_short_16","alias_value":"4V2LNT7SASOTSVP6","created_at":"2026-07-05T01:43:23Z"},{"alias_kind":"pith_short_8","alias_value":"4V2LNT7S","created_at":"2026-07-05T01:43:23Z"}],"graph_snapshots":[{"event_id":"sha256:e0edf9749d195183500233a18700bdae0868deeb1cbe53b053eddd232d01b062","target":"graph","created_at":"2026-07-05T01:43:23Z","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/1912.01557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entropy regularization is an important idea in reinforcement learning, with great success in recent algorithms like Soft Q Network (SQN) and Soft Actor-Critic (SAC1). In this work, we extend this idea into the on-policy realm. We propose the soft policy gradient theorem (SPGT) for on-policy maximum entropy reinforcement learning. With SPGT, a series of new policy optimization algorithms are derived, such as SPG, SA2C, SA3C, SDDPG, STRPO, SPPO, SIMPALA and so on. We find that SDDPG is equivalent to SAC1. For policy gradient, the policy network is often represented as a Gaussian distribution wit","authors_text":"Jingbin Liu, Shuai Liu, Xinyang Gu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-02T11:01:32Z","title":"Policy Optimization Reinforcement Learning with Entropy Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.01557","kind":"arxiv","version":3},"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":"sha256:2d69834b68eb82f50e1c7cc181534b88ce0bc6361a2bb606796cf50b2530f870","target":"record","created_at":"2026-07-05T01:43:23Z","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":"ed58542178b41b00b87daad2405696a67380acf7a135187a0be7269601309803","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-02T11:01:32Z","title_canon_sha256":"5864412765c9ef1a5b91ee6a5b213e86f3b9f316c28248fcc942e3603b46ed5e"},"schema_version":"1.0","source":{"id":"1912.01557","kind":"arxiv","version":3}},"canonical_sha256":"e574b6cff2049d3955fe673fab8bc782de716159d37e0a6144fa9e896428901c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e574b6cff2049d3955fe673fab8bc782de716159d37e0a6144fa9e896428901c","first_computed_at":"2026-07-05T01:43:23.897326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:23.897326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tEgzPfCOSrJUb+Fj/D3/k8JvLXqnoYp9mlle6AvSEGutFXFhC3c5MTXlT+CKRosMirlIqKaPJuT/GiX9SIQQAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:23.897806Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.01557","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d69834b68eb82f50e1c7cc181534b88ce0bc6361a2bb606796cf50b2530f870","sha256:e0edf9749d195183500233a18700bdae0868deeb1cbe53b053eddd232d01b062"],"state_sha256":"04eddfef0fa291ea44cccbfcfe7ec3482c2dab68ff762509a051805e32ab7a22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LFOW6KcOz9WmDUHTnDsh3FK8V5F3P1otklUzP8ofEuqiarulmuxvS7KCtImTuPH3/1AD+iPDazyp0srF1S0TDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:05:43.907743Z","bundle_sha256":"aa0e978c820bbbc30bcbc077c8532a82268376f3ccde3d6c67373c306a0ef035"}}