{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PRQAOVWUPVBJG524SQGQOQ3KDY","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":"cd3ed21c2f26b888133dc91e0401953be6be0d44b712b873870419826bb98b44","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-01T11:06:04Z","title_canon_sha256":"042fb9fc9c38c2da754f299668be67a8d4b7c6e430e072d19d28696a6c0dd711"},"schema_version":"1.0","source":{"id":"1705.00470","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.00470","created_at":"2026-05-18T00:38:27Z"},{"alias_kind":"arxiv_version","alias_value":"1705.00470v2","created_at":"2026-05-18T00:38:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00470","created_at":"2026-05-18T00:38:27Z"},{"alias_kind":"pith_short_12","alias_value":"PRQAOVWUPVBJ","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PRQAOVWUPVBJG524","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PRQAOVWU","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:aa1eaa65bc946ea436f3d07c3ef42639c836678d6fb85b03b5996c487cbab700","target":"graph","created_at":"2026-05-18T00:38:27Z","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 this paper we study how to learn stochastic, multimodal transition dynamics in reinforcement learning (RL) tasks. We focus on evaluating transition function estimation, while we defer planning over this model to future work. Stochasticity is a fundamental property of many task environments. However, discriminative function approximators have difficulty estimating multimodal stochasticity. In contrast, deep generative models do capture complex high-dimensional outcome distributions. First we discuss why, amongst such models, conditional variational inference (VI) is theoretically most appeal","authors_text":"Catholijn M. Jonker, Joost Broekens, Thomas M. Moerland","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-01T11:06:04Z","title":"Learning Multimodal Transition Dynamics for Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00470","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":"sha256:9667e2feff226eb6bfb12b2bab57a1272d12695dde0a2ee6c26dff698ebad1e7","target":"record","created_at":"2026-05-18T00:38:27Z","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":"cd3ed21c2f26b888133dc91e0401953be6be0d44b712b873870419826bb98b44","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-01T11:06:04Z","title_canon_sha256":"042fb9fc9c38c2da754f299668be67a8d4b7c6e430e072d19d28696a6c0dd711"},"schema_version":"1.0","source":{"id":"1705.00470","kind":"arxiv","version":2}},"canonical_sha256":"7c600756d47d4293775c940d07436a1e02a59b0b78804d54620ae41fa7dfb1e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c600756d47d4293775c940d07436a1e02a59b0b78804d54620ae41fa7dfb1e9","first_computed_at":"2026-05-18T00:38:27.392973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:27.392973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"86WhD9bFIFlMItZolLtxBwjQBJ+m+1JEwbf3xL5ipQwkaqkWGllOgT9nc+sDVjF79pAYu+/m80VeFDgFZJSICw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:27.393584Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.00470","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9667e2feff226eb6bfb12b2bab57a1272d12695dde0a2ee6c26dff698ebad1e7","sha256:aa1eaa65bc946ea436f3d07c3ef42639c836678d6fb85b03b5996c487cbab700"],"state_sha256":"e2e8918acb92496b208c228fe0ebb4f8a2f7ab726e2263042a7366918e0d206e"}