{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DM7RT4OLP4QAVMHEAJQ5FXRP67","short_pith_number":"pith:DM7RT4OL","canonical_record":{"source":{"id":"1912.05128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T05:55:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b7b37843ce28452bfab246cfa02d6f946be2ddddff7fe46e0b15d36754ee27c6","abstract_canon_sha256":"eebcceafa333e86a1740e4c54c40b93b55fe16daef0573a019d1ecbda433b184"},"schema_version":"1.0"},"canonical_sha256":"1b3f19f1cb7f200ab0e40261d2de2ff7de0923308f704c6cc7aed4733eab8e6d","source":{"kind":"arxiv","id":"1912.05128","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05128","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05128v1","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05128","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"DM7RT4OLP4QA","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"pith_short_16","alias_value":"DM7RT4OLP4QAVMHE","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"pith_short_8","alias_value":"DM7RT4OL","created_at":"2026-07-05T00:25:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DM7RT4OLP4QAVMHEAJQ5FXRP67","target":"record","payload":{"canonical_record":{"source":{"id":"1912.05128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T05:55:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b7b37843ce28452bfab246cfa02d6f946be2ddddff7fe46e0b15d36754ee27c6","abstract_canon_sha256":"eebcceafa333e86a1740e4c54c40b93b55fe16daef0573a019d1ecbda433b184"},"schema_version":"1.0"},"canonical_sha256":"1b3f19f1cb7f200ab0e40261d2de2ff7de0923308f704c6cc7aed4733eab8e6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:32.401261Z","signature_b64":"DEaXo5G4Rh/tunRssj3C9dKRyzAxyuGcPgUFjDUU9lYj19AjTtF+3zcFnH7cySlHvQytEEj3H6Tql1mFklGVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b3f19f1cb7f200ab0e40261d2de2ff7de0923308f704c6cc7aed4733eab8e6d","last_reissued_at":"2026-07-05T00:25:32.400918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:32.400918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.05128","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":"2026-07-05T00:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XGDc/mnk0hlSzu4WGJrOCyIwlTDHxqYUD8y2TZ7zgpyouJeMXZsQaCkEm+q1B6DOsTKFIZX12k6vlLjXLPaGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:48:26.097316Z"},"content_sha256":"f5fd5e2355a6f59e9de62e82f258344d6bea0ab6f9dab30d22f4dcef332c3d95","schema_version":"1.0","event_id":"sha256:f5fd5e2355a6f59e9de62e82f258344d6bea0ab6f9dab30d22f4dcef332c3d95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DM7RT4OLP4QAVMHEAJQ5FXRP67","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Marginalized State Distribution Entropy Regularization in Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Riashat Islam, Zafarali Ahmed","submitted_at":"2019-12-11T05:55:32Z","abstract_excerpt":"Entropy regularization is used to get improved optimization performance in reinforcement learning tasks. A common form of regularization is to maximize policy entropy to avoid premature convergence and lead to more stochastic policies for exploration through action space. However, this does not ensure exploration in the state space. In this work, we instead consider the distribution of discounted weighting of states, and propose to maximize the entropy of a lower bound approximation to the weighting of a state, based on latent space state representation. We propose entropy regularization based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05128","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.05128/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":"2026-07-05T00:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yn6aomKY5qQjLUBtDBT+KIM9tr+MHQtWrQHazndKplCmlabtlJeQoHikkwCGu/0w3beleBiE0/LYm6o9h1iBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:48:26.097862Z"},"content_sha256":"b64c171fc9e84a26b40168d8aeed65044bce5f32df1ba74e7f814b2966fe829b","schema_version":"1.0","event_id":"sha256:b64c171fc9e84a26b40168d8aeed65044bce5f32df1ba74e7f814b2966fe829b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DM7RT4OLP4QAVMHEAJQ5FXRP67/bundle.json","state_url":"https://pith.science/pith/DM7RT4OLP4QAVMHEAJQ5FXRP67/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DM7RT4OLP4QAVMHEAJQ5FXRP67/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":"2026-08-06T08:48:26Z","links":{"resolver":"https://pith.science/pith/DM7RT4OLP4QAVMHEAJQ5FXRP67","bundle":"https://pith.science/pith/DM7RT4OLP4QAVMHEAJQ5FXRP67/bundle.json","state":"https://pith.science/pith/DM7RT4OLP4QAVMHEAJQ5FXRP67/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DM7RT4OLP4QAVMHEAJQ5FXRP67/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DM7RT4OLP4QAVMHEAJQ5FXRP67","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":"eebcceafa333e86a1740e4c54c40b93b55fe16daef0573a019d1ecbda433b184","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T05:55:32Z","title_canon_sha256":"b7b37843ce28452bfab246cfa02d6f946be2ddddff7fe46e0b15d36754ee27c6"},"schema_version":"1.0","source":{"id":"1912.05128","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05128","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05128v1","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05128","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"DM7RT4OLP4QA","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"pith_short_16","alias_value":"DM7RT4OLP4QAVMHE","created_at":"2026-07-05T00:25:32Z"},{"alias_kind":"pith_short_8","alias_value":"DM7RT4OL","created_at":"2026-07-05T00:25:32Z"}],"graph_snapshots":[{"event_id":"sha256:b64c171fc9e84a26b40168d8aeed65044bce5f32df1ba74e7f814b2966fe829b","target":"graph","created_at":"2026-07-05T00:25:32Z","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/1912.05128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entropy regularization is used to get improved optimization performance in reinforcement learning tasks. A common form of regularization is to maximize policy entropy to avoid premature convergence and lead to more stochastic policies for exploration through action space. However, this does not ensure exploration in the state space. In this work, we instead consider the distribution of discounted weighting of states, and propose to maximize the entropy of a lower bound approximation to the weighting of a state, based on latent space state representation. We propose entropy regularization based","authors_text":"Doina Precup, Riashat Islam, Zafarali Ahmed","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T05:55:32Z","title":"Marginalized State Distribution Entropy Regularization in Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05128","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:f5fd5e2355a6f59e9de62e82f258344d6bea0ab6f9dab30d22f4dcef332c3d95","target":"record","created_at":"2026-07-05T00:25:32Z","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":"eebcceafa333e86a1740e4c54c40b93b55fe16daef0573a019d1ecbda433b184","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-11T05:55:32Z","title_canon_sha256":"b7b37843ce28452bfab246cfa02d6f946be2ddddff7fe46e0b15d36754ee27c6"},"schema_version":"1.0","source":{"id":"1912.05128","kind":"arxiv","version":1}},"canonical_sha256":"1b3f19f1cb7f200ab0e40261d2de2ff7de0923308f704c6cc7aed4733eab8e6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b3f19f1cb7f200ab0e40261d2de2ff7de0923308f704c6cc7aed4733eab8e6d","first_computed_at":"2026-07-05T00:25:32.400918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:25:32.400918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DEaXo5G4Rh/tunRssj3C9dKRyzAxyuGcPgUFjDUU9lYj19AjTtF+3zcFnH7cySlHvQytEEj3H6Tql1mFklGVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:25:32.401261Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.05128","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5fd5e2355a6f59e9de62e82f258344d6bea0ab6f9dab30d22f4dcef332c3d95","sha256:b64c171fc9e84a26b40168d8aeed65044bce5f32df1ba74e7f814b2966fe829b"],"state_sha256":"455e37bbd9517323a8667a97fd228919350b7fe176cc92bf5470f5281dc6d703"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DaZY8iHr3DGObsbqt33hDnT7e8jEVY3rimWgme7qCmoo1KMdkhA2Dzxcdu6EENvRcJ7sWGtry2xzjalRMUnrBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:48:26.102193Z","bundle_sha256":"e300c577581f1961ebeb1d74cab211d1d4888d27306966acc7c436864d746722"}}