{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:G3QHYBHTGTXLTU3DYKIKFVYWIN","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":"88eaad04b796ebccb085623f9d8f915dcb643a5c41f23d0f8e4edbf51d96ae2d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T02:25:51Z","title_canon_sha256":"d7cad5828001e6025f70baaf96dea3f28a964c77d375d9c05735c10908b82bef"},"schema_version":"1.0","source":{"id":"2008.02430","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.02430","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"2008.02430v2","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02430","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"G3QHYBHTGTXL","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"pith_short_16","alias_value":"G3QHYBHTGTXLTU3D","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"pith_short_8","alias_value":"G3QHYBHT","created_at":"2026-07-05T01:49:54Z"}],"graph_snapshots":[{"event_id":"sha256:d10f9cb951c9cc1d8584d039dcde22730889e4f4d01f13e66f09f5800824171e","target":"graph","created_at":"2026-07-05T01:49:54Z","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/2008.02430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (DRL) has achieved significant success in various robot tasks: manipulation, navigation, etc. However, complex visual observations in natural environments remains a major challenge. This paper presents Contrastive Variational Reinforcement Learning (CVRL), a model-based method that tackles complex visual observations in DRL. CVRL learns a contrastive variational model by maximizing the mutual information between latent states and observations discriminatively, through contrastive learning. It avoids modeling the complex observation space unnecessarily, as the common","authors_text":"David Hsu, Siwei Chen, Wee Sun Lee, Xiao Ma","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T02:25:51Z","title":"Contrastive Variational Reinforcement Learning for Complex Observations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02430","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:c45d5059a7ff9b3e9babf8c69a414563cec4bd7ebaabc1c98621c36ac8648d52","target":"record","created_at":"2026-07-05T01:49:54Z","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":"88eaad04b796ebccb085623f9d8f915dcb643a5c41f23d0f8e4edbf51d96ae2d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T02:25:51Z","title_canon_sha256":"d7cad5828001e6025f70baaf96dea3f28a964c77d375d9c05735c10908b82bef"},"schema_version":"1.0","source":{"id":"2008.02430","kind":"arxiv","version":2}},"canonical_sha256":"36e07c04f334eeb9d363c290a2d716434dbdf76e5a2999ff461224264ce5de70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36e07c04f334eeb9d363c290a2d716434dbdf76e5a2999ff461224264ce5de70","first_computed_at":"2026-07-05T01:49:54.036828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:54.036828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cAYvIJi98kEaTaJRxNK+nLtRNhCPei7iylOozCfBiI3+M4fXTtZshi9ivXGAZuJaqFnr3YqqoJsoX1/RO6R9AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:54.037208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.02430","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c45d5059a7ff9b3e9babf8c69a414563cec4bd7ebaabc1c98621c36ac8648d52","sha256:d10f9cb951c9cc1d8584d039dcde22730889e4f4d01f13e66f09f5800824171e"],"state_sha256":"8783a46b681fa997ac0fb3c393f2bb3d76d7e54874d099f65629b6ca912dc75d"}