{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:W4WDO6ITWT3PUXLPNDTLWLCXNX","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":"b3ea90a6997c25db86d4fa308fd1f3748db3b22e564c72e3ac70f0a311026de0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-10T18:55:19Z","title_canon_sha256":"67906a16f10fac88d8d372c649cdb4f5882d362b83057c4b250769f526bc3622"},"schema_version":"1.0","source":{"id":"1809.03548","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.03548","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"1809.03548v2","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03548","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"W4WDO6ITWT3P","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"W4WDO6ITWT3PUXLP","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"W4WDO6IT","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:983139a09fcc098266f0ffa6c12fd724c94f83e09d97c145e40ec51bacad90b0","target":"graph","created_at":"2026-05-18T00:05:44Z","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":"Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and data collection is expensive, making retraining undesirable. Simulation training allows for feasible training times, but on the other hand suffers from a reality-gap when applied in real-world settings. This raises the need of efficient adaptation of policies acting in new environments. We consider this as a problem of transferring knowledge within a family ","authors_text":"Danica Kragic, Isac Arnekvist, Johannes A. Stork","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-10T18:55:19Z","title":"VPE: Variational Policy Embedding for Transfer Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03548","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:f243853943e2c7ca06a0c7fe058d5a5709ada5d67219bbf83a6eb64d5747c64d","target":"record","created_at":"2026-05-18T00:05:44Z","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":"b3ea90a6997c25db86d4fa308fd1f3748db3b22e564c72e3ac70f0a311026de0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-10T18:55:19Z","title_canon_sha256":"67906a16f10fac88d8d372c649cdb4f5882d362b83057c4b250769f526bc3622"},"schema_version":"1.0","source":{"id":"1809.03548","kind":"arxiv","version":2}},"canonical_sha256":"b72c377913b4f6fa5d6f68e6bb2c576dde806a6baf40825dc010c670b5222ed3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b72c377913b4f6fa5d6f68e6bb2c576dde806a6baf40825dc010c670b5222ed3","first_computed_at":"2026-05-18T00:05:44.831066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:44.831066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+AMWWUnp64zRC9SlBRZgudgZ9Fg/hEwIxx+BEt9QZG+kIDTuo5lQ5BGjr2weubzTStfla6bHTlfy+WS+7SWtCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:44.831792Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.03548","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f243853943e2c7ca06a0c7fe058d5a5709ada5d67219bbf83a6eb64d5747c64d","sha256:983139a09fcc098266f0ffa6c12fd724c94f83e09d97c145e40ec51bacad90b0"],"state_sha256":"dead53bfbf380242caae6db17152ee2b172dd7c1fcc3e96a9c62cd25fc1e3ac1"}