{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IREHLT72ECYHCK75322HLYSZYD","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":"aa8875e8f9e10bb4845c3f044d265c66cc2a0f5e4824e90b79cdb8ae5fb2065e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-01T17:45:09Z","title_canon_sha256":"e72201c5a104b941510e1d1a26c94b9ed61f8ce5d8c5870e28c9162efe755637"},"schema_version":"1.0","source":{"id":"1907.00953","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.00953","created_at":"2026-07-05T01:45:58Z"},{"alias_kind":"arxiv_version","alias_value":"1907.00953v4","created_at":"2026-07-05T01:45:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00953","created_at":"2026-07-05T01:45:58Z"},{"alias_kind":"pith_short_12","alias_value":"IREHLT72ECYH","created_at":"2026-07-05T01:45:58Z"},{"alias_kind":"pith_short_16","alias_value":"IREHLT72ECYHCK75","created_at":"2026-07-05T01:45:58Z"},{"alias_kind":"pith_short_8","alias_value":"IREHLT72","created_at":"2026-07-05T01:45:58Z"}],"graph_snapshots":[{"event_id":"sha256:6af6c7529dd88a714e5757bdb24a5abe2053d9a1c4c82aa16513432e026341c9","target":"graph","created_at":"2026-07-05T01:45:58Z","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/1907.00953/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn directly from image observations. However, these high-dimensional observation spaces present a number of challenges in practice, since the policy must now solve two problems: representation learning and task learning. In this work, we tackle these two problems separately, by explicitly learning latent representations that can accelerate reinforcement learning from images. We propose the stochastic latent actor-critic (SLAC) algorithm: a sample-efficient and high-performing RL algorithm for learning policie","authors_text":"Alex X. Lee, Anusha Nagabandi, Pieter Abbeel, Sergey Levine","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-01T17:45:09Z","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00953","kind":"arxiv","version":4},"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:c4cf9f3c96e5d4163524e15585c2d0807fa3fa6402a14eebed92af575d26cf88","target":"record","created_at":"2026-07-05T01:45:58Z","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":"aa8875e8f9e10bb4845c3f044d265c66cc2a0f5e4824e90b79cdb8ae5fb2065e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-01T17:45:09Z","title_canon_sha256":"e72201c5a104b941510e1d1a26c94b9ed61f8ce5d8c5870e28c9162efe755637"},"schema_version":"1.0","source":{"id":"1907.00953","kind":"arxiv","version":4}},"canonical_sha256":"444875cffa20b0712bfddeb475e259c0d63c58c2ad4bd49c8fbe14ee8a611f4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"444875cffa20b0712bfddeb475e259c0d63c58c2ad4bd49c8fbe14ee8a611f4e","first_computed_at":"2026-07-05T01:45:58.961528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:58.961528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b6SCCWavsSlo3MQtfVwtNLtRXn7lUKzuTvWh2W+QCjb3q+Bd6a1K2WknJZHo3g5rnh2Owceyi0d2fyvG4zeNDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:58.962020Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.00953","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4cf9f3c96e5d4163524e15585c2d0807fa3fa6402a14eebed92af575d26cf88","sha256:6af6c7529dd88a714e5757bdb24a5abe2053d9a1c4c82aa16513432e026341c9"],"state_sha256":"0a3f08756281d0c24f28a4f73ef64b7da2dacac7b6465cc34ea5557db2ac31e5"}