{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IREHLT72ECYHCK75322HLYSZYD","short_pith_number":"pith:IREHLT72","schema_version":"1.0","canonical_sha256":"444875cffa20b0712bfddeb475e259c0d63c58c2ad4bd49c8fbe14ee8a611f4e","source":{"kind":"arxiv","id":"1907.00953","version":4},"attestation_state":"computed","paper":{"title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex X. Lee, Anusha Nagabandi, Pieter Abbeel, Sergey Levine","submitted_at":"2019-07-01T17:45:09Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1907.00953","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-01T17:45:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e72201c5a104b941510e1d1a26c94b9ed61f8ce5d8c5870e28c9162efe755637","abstract_canon_sha256":"aa8875e8f9e10bb4845c3f044d265c66cc2a0f5e4824e90b79cdb8ae5fb2065e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:58.962020Z","signature_b64":"b6SCCWavsSlo3MQtfVwtNLtRXn7lUKzuTvWh2W+QCjb3q+Bd6a1K2WknJZHo3g5rnh2Owceyi0d2fyvG4zeNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"444875cffa20b0712bfddeb475e259c0d63c58c2ad4bd49c8fbe14ee8a611f4e","last_reissued_at":"2026-07-05T01:45:58.961528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:58.961528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex X. Lee, Anusha Nagabandi, Pieter Abbeel, Sergey Levine","submitted_at":"2019-07-01T17:45:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00953","kind":"arxiv","version":4},"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/1907.00953/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1907.00953","created_at":"2026-07-05T01:45:58.961583+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.00953v4","created_at":"2026-07-05T01:45:58.961583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00953","created_at":"2026-07-05T01:45:58.961583+00:00"},{"alias_kind":"pith_short_12","alias_value":"IREHLT72ECYH","created_at":"2026-07-05T01:45:58.961583+00:00"},{"alias_kind":"pith_short_16","alias_value":"IREHLT72ECYHCK75","created_at":"2026-07-05T01:45:58.961583+00:00"},{"alias_kind":"pith_short_8","alias_value":"IREHLT72","created_at":"2026-07-05T01:45:58.961583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.14427","citing_title":"Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2010.02193","citing_title":"Mastering Atari with Discrete World Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"1912.01603","citing_title":"Dream to Control: Learning Behaviors by Latent Imagination","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IREHLT72ECYHCK75322HLYSZYD","json":"https://pith.science/pith/IREHLT72ECYHCK75322HLYSZYD.json","graph_json":"https://pith.science/api/pith-number/IREHLT72ECYHCK75322HLYSZYD/graph.json","events_json":"https://pith.science/api/pith-number/IREHLT72ECYHCK75322HLYSZYD/events.json","paper":"https://pith.science/paper/IREHLT72"},"agent_actions":{"view_html":"https://pith.science/pith/IREHLT72ECYHCK75322HLYSZYD","download_json":"https://pith.science/pith/IREHLT72ECYHCK75322HLYSZYD.json","view_paper":"https://pith.science/paper/IREHLT72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.00953&json=true","fetch_graph":"https://pith.science/api/pith-number/IREHLT72ECYHCK75322HLYSZYD/graph.json","fetch_events":"https://pith.science/api/pith-number/IREHLT72ECYHCK75322HLYSZYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IREHLT72ECYHCK75322HLYSZYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IREHLT72ECYHCK75322HLYSZYD/action/storage_attestation","attest_author":"https://pith.science/pith/IREHLT72ECYHCK75322HLYSZYD/action/author_attestation","sign_citation":"https://pith.science/pith/IREHLT72ECYHCK75322HLYSZYD/action/citation_signature","submit_replication":"https://pith.science/pith/IREHLT72ECYHCK75322HLYSZYD/action/replication_record"}},"created_at":"2026-07-05T01:45:58.961583+00:00","updated_at":"2026-07-05T01:45:58.961583+00:00"}