{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:Z4WR6H3X3OIJ766S3EOHRGYTFR","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":"a42de9c9b8618644d97449ed968dd56f670ebdb65a0e08c2f201702fe3196918","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-05T00:15:21Z","title_canon_sha256":"055d749ad3bc391c612c7536f754723d12efdf915f480dba3cfd873201b3bbeb"},"schema_version":"1.0","source":{"id":"1903.01599","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.01599","created_at":"2026-05-17T23:51:09Z"},{"alias_kind":"arxiv_version","alias_value":"1903.01599v2","created_at":"2026-05-17T23:51:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.01599","created_at":"2026-05-17T23:51:09Z"},{"alias_kind":"pith_short_12","alias_value":"Z4WR6H3X3OIJ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"Z4WR6H3X3OIJ766S","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"Z4WR6H3X","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:5ca2c6e32902474500bfadf83b6eda75b759dd6a1bd3192c087007879439e2a9","target":"graph","created_at":"2026-05-17T23:51:09Z","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"},"paper":{"abstract_excerpt":"In model-based reinforcement learning, the agent interleaves between model learning and planning. These two components are inextricably intertwined. If the model is not able to provide sensible long-term prediction, the executed planner would exploit model flaws, which can yield catastrophic failures. This paper focuses on building a model that reasons about the long-term future and demonstrates how to use this for efficient planning and exploration. To this end, we build a latent-variable autoregressive model by leveraging recent ideas in variational inference. We argue that forcing latent va","authors_text":"Ahmed Touati, Amanpreet Singh, Anirudh Goyal, Devi Parikh, Dhruv Batra, Nan Rosemary Ke, Yoshua Bengio","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-05T00:15:21Z","title":"Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.01599","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":"sha256:360efea72c5b71409e6080b235a4871c58349b9b46708f66de69d5ef982056f7","target":"record","created_at":"2026-05-17T23:51:09Z","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":"a42de9c9b8618644d97449ed968dd56f670ebdb65a0e08c2f201702fe3196918","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-05T00:15:21Z","title_canon_sha256":"055d749ad3bc391c612c7536f754723d12efdf915f480dba3cfd873201b3bbeb"},"schema_version":"1.0","source":{"id":"1903.01599","kind":"arxiv","version":2}},"canonical_sha256":"cf2d1f1f77db909ffbd2d91c789b132c5494ac92a388a06b269a6c1443bcc298","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf2d1f1f77db909ffbd2d91c789b132c5494ac92a388a06b269a6c1443bcc298","first_computed_at":"2026-05-17T23:51:09.294026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:09.294026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/NRdBIS0PJkS4EHSC06j28PaHQHmheKnLnmsTQTo+nzgh+llmrxM1NedO+9nVYY+EnfewPcsbtKfkjqZbL6LDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:09.294511Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.01599","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:360efea72c5b71409e6080b235a4871c58349b9b46708f66de69d5ef982056f7","sha256:5ca2c6e32902474500bfadf83b6eda75b759dd6a1bd3192c087007879439e2a9"],"state_sha256":"e46d35b04f5065712757794309e1699f779d19f66e8016009e4d295f4267ef10"}