{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3QS5INCNS7RLZFGAMED5TQ7ZK2","short_pith_number":"pith:3QS5INCN","canonical_record":{"source":{"id":"2210.00999","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T15:09:12Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e9ffbad9f90915d07989989468f5d2ff7071569a6f5661babea0a15a1971ef7b","abstract_canon_sha256":"9da1e1723485904788bb0041aeb4db7b122f9db164ffdb22f8a4f22385dd2460"},"schema_version":"1.0"},"canonical_sha256":"dc25d4344d97e2bc94c06107d9c3f9569cffcb97c8a553186f41a2dbda094885","source":{"kind":"arxiv","id":"2210.00999","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.00999","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"arxiv_version","alias_value":"2210.00999v2","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00999","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"pith_short_12","alias_value":"3QS5INCNS7RL","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"pith_short_16","alias_value":"3QS5INCNS7RLZFGA","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"pith_short_8","alias_value":"3QS5INCN","created_at":"2026-07-05T05:40:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3QS5INCNS7RLZFGAMED5TQ7ZK2","target":"record","payload":{"canonical_record":{"source":{"id":"2210.00999","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T15:09:12Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e9ffbad9f90915d07989989468f5d2ff7071569a6f5661babea0a15a1971ef7b","abstract_canon_sha256":"9da1e1723485904788bb0041aeb4db7b122f9db164ffdb22f8a4f22385dd2460"},"schema_version":"1.0"},"canonical_sha256":"dc25d4344d97e2bc94c06107d9c3f9569cffcb97c8a553186f41a2dbda094885","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:32.449262Z","signature_b64":"4e1oLSNiMqo8OMdgisKVHEs2xSttaf447ChHwJjC+zilmI6hoqj1iSjuiwvL5Vnctmef5ErTHrNZEjC2091MCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc25d4344d97e2bc94c06107d9c3f9569cffcb97c8a553186f41a2dbda094885","last_reissued_at":"2026-07-05T05:40:32.448809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:32.448809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.00999","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:40:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0139aeGcAX1WYIpH4DO8qXWepW27sQ7br7MgvA/YXH0S0btCMgoR7ivsXgfQ8SQtaQNlTYLV4BW3Rpco0CiUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:46:37.645308Z"},"content_sha256":"4858a5f6fde14ca7ebc7bd0c30a67178463ce74fb6dbf7e0e6a3e09d2fd749af","schema_version":"1.0","event_id":"sha256:4858a5f6fde14ca7ebc7bd0c30a67178463ce74fb6dbf7e0e6a3e09d2fd749af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3QS5INCNS7RLZFGAMED5TQ7ZK2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent State Marginalization as a Low-cost Approach for Improving Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Amy Zhang, Dinghuai Zhang, Qinqing Zheng, Ricky T. Q. Chen, Yoshua Bengio","submitted_at":"2022-10-03T15:09:12Z","abstract_excerpt":"While the maximum entropy (MaxEnt) reinforcement learning (RL) framework -- often touted for its exploration and robustness capabilities -- is usually motivated from a probabilistic perspective, the use of deep probabilistic models has not gained much traction in practice due to their inherent complexity. In this work, we propose the adoption of latent variable policies within the MaxEnt framework, which we show can provably approximate any policy distribution, and additionally, naturally emerges under the use of world models with a latent belief state. We discuss why latent variable policies "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00999","kind":"arxiv","version":2},"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/2210.00999/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":"2026-07-05T05:40:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+d6TN+BwCXIJ7HvqK30g7RIFKsb4Z+V5P7tdwPqrg6B10JAPKXWH9IzUNhQYBUWK+HY6/Fk8JQFITYO7+NGfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:46:37.646265Z"},"content_sha256":"1c4448a1a8d169621f6cdabb4312832e5a58683086c6e69e83f6a6065bb887fe","schema_version":"1.0","event_id":"sha256:1c4448a1a8d169621f6cdabb4312832e5a58683086c6e69e83f6a6065bb887fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3QS5INCNS7RLZFGAMED5TQ7ZK2/bundle.json","state_url":"https://pith.science/pith/3QS5INCNS7RLZFGAMED5TQ7ZK2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3QS5INCNS7RLZFGAMED5TQ7ZK2/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":"2026-08-08T19:46:37Z","links":{"resolver":"https://pith.science/pith/3QS5INCNS7RLZFGAMED5TQ7ZK2","bundle":"https://pith.science/pith/3QS5INCNS7RLZFGAMED5TQ7ZK2/bundle.json","state":"https://pith.science/pith/3QS5INCNS7RLZFGAMED5TQ7ZK2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3QS5INCNS7RLZFGAMED5TQ7ZK2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3QS5INCNS7RLZFGAMED5TQ7ZK2","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":"9da1e1723485904788bb0041aeb4db7b122f9db164ffdb22f8a4f22385dd2460","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T15:09:12Z","title_canon_sha256":"e9ffbad9f90915d07989989468f5d2ff7071569a6f5661babea0a15a1971ef7b"},"schema_version":"1.0","source":{"id":"2210.00999","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.00999","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"arxiv_version","alias_value":"2210.00999v2","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00999","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"pith_short_12","alias_value":"3QS5INCNS7RL","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"pith_short_16","alias_value":"3QS5INCNS7RLZFGA","created_at":"2026-07-05T05:40:32Z"},{"alias_kind":"pith_short_8","alias_value":"3QS5INCN","created_at":"2026-07-05T05:40:32Z"}],"graph_snapshots":[{"event_id":"sha256:1c4448a1a8d169621f6cdabb4312832e5a58683086c6e69e83f6a6065bb887fe","target":"graph","created_at":"2026-07-05T05:40:32Z","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/2210.00999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While the maximum entropy (MaxEnt) reinforcement learning (RL) framework -- often touted for its exploration and robustness capabilities -- is usually motivated from a probabilistic perspective, the use of deep probabilistic models has not gained much traction in practice due to their inherent complexity. In this work, we propose the adoption of latent variable policies within the MaxEnt framework, which we show can provably approximate any policy distribution, and additionally, naturally emerges under the use of world models with a latent belief state. We discuss why latent variable policies ","authors_text":"Aaron Courville, Amy Zhang, Dinghuai Zhang, Qinqing Zheng, Ricky T. Q. Chen, Yoshua Bengio","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T15:09:12Z","title":"Latent State Marginalization as a Low-cost Approach for Improving Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00999","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":"sha256:4858a5f6fde14ca7ebc7bd0c30a67178463ce74fb6dbf7e0e6a3e09d2fd749af","target":"record","created_at":"2026-07-05T05:40:32Z","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":"9da1e1723485904788bb0041aeb4db7b122f9db164ffdb22f8a4f22385dd2460","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T15:09:12Z","title_canon_sha256":"e9ffbad9f90915d07989989468f5d2ff7071569a6f5661babea0a15a1971ef7b"},"schema_version":"1.0","source":{"id":"2210.00999","kind":"arxiv","version":2}},"canonical_sha256":"dc25d4344d97e2bc94c06107d9c3f9569cffcb97c8a553186f41a2dbda094885","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc25d4344d97e2bc94c06107d9c3f9569cffcb97c8a553186f41a2dbda094885","first_computed_at":"2026-07-05T05:40:32.448809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:32.448809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4e1oLSNiMqo8OMdgisKVHEs2xSttaf447ChHwJjC+zilmI6hoqj1iSjuiwvL5Vnctmef5ErTHrNZEjC2091MCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:32.449262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.00999","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4858a5f6fde14ca7ebc7bd0c30a67178463ce74fb6dbf7e0e6a3e09d2fd749af","sha256:1c4448a1a8d169621f6cdabb4312832e5a58683086c6e69e83f6a6065bb887fe"],"state_sha256":"c65cf249c4f66589cd4212ea1b894b00ca37e6a3d1dccd2fb71bb79eacdac5ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g1Fw3pyB5anszgNEve4LlFs3DOgD2FRl6I8Dc8TPIms2pHYEbmGol+8cdy1x/j6Xr9YCXRWXNpdE8owHJRMyBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:46:37.652210Z","bundle_sha256":"676b9028ca8d1cc91285418d842834153c821384d32350522ce4e9160df955ea"}}