{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IEJNU326MCSSCF6O74JC5JJJYK","short_pith_number":"pith:IEJNU326","schema_version":"1.0","canonical_sha256":"4112da6f5e60a52117ceff122ea529c2877f2d05679aa7ecdaa5283d4d32d45c","source":{"kind":"arxiv","id":"2311.06673","version":1},"attestation_state":"computed","paper":{"title":"Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"H. Eric Tseng, Huei Peng, Lu Wen, Songan Zhang","submitted_at":"2023-11-11T22:05:10Z","abstract_excerpt":"Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-training tasks to have a dense coverage on the task distribution and a great amount of data for each of them. In this paper, we propose MetaDreamer, a context-based Meta RL algorithm that requires less real training tasks and data by doing meta-imagination and MDP-imagination. We perform meta-imagination by interpolating on the learned latent context space with disentangled prope"},"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":"2311.06673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-11T22:05:10Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"94483fbedb2acf836704453421ff5a2203ae4ec996ee5349916b38cfa694b0ef","abstract_canon_sha256":"83150f34990d6484725815051db20d85f1e9f3b8a97808f826c7fb527a76158a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:43.641364Z","signature_b64":"0pXNUEM/xfOclhsFIGEgxwWfidO65YCzbWlX+P6CdeyAJ2Ltv0lfv1V0zYnR/mWdn+vZzwuyamJXRKK+OZOIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4112da6f5e60a52117ceff122ea529c2877f2d05679aa7ecdaa5283d4d32d45c","last_reissued_at":"2026-07-05T07:11:43.640831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:43.640831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"H. Eric Tseng, Huei Peng, Lu Wen, Songan Zhang","submitted_at":"2023-11-11T22:05:10Z","abstract_excerpt":"Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-training tasks to have a dense coverage on the task distribution and a great amount of data for each of them. In this paper, we propose MetaDreamer, a context-based Meta RL algorithm that requires less real training tasks and data by doing meta-imagination and MDP-imagination. We perform meta-imagination by interpolating on the learned latent context space with disentangled prope"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06673","kind":"arxiv","version":1},"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/2311.06673/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":"2311.06673","created_at":"2026-07-05T07:11:43.640890+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06673v1","created_at":"2026-07-05T07:11:43.640890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06673","created_at":"2026-07-05T07:11:43.640890+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEJNU326MCSS","created_at":"2026-07-05T07:11:43.640890+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEJNU326MCSSCF6O","created_at":"2026-07-05T07:11:43.640890+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEJNU326","created_at":"2026-07-05T07:11:43.640890+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IEJNU326MCSSCF6O74JC5JJJYK","json":"https://pith.science/pith/IEJNU326MCSSCF6O74JC5JJJYK.json","graph_json":"https://pith.science/api/pith-number/IEJNU326MCSSCF6O74JC5JJJYK/graph.json","events_json":"https://pith.science/api/pith-number/IEJNU326MCSSCF6O74JC5JJJYK/events.json","paper":"https://pith.science/paper/IEJNU326"},"agent_actions":{"view_html":"https://pith.science/pith/IEJNU326MCSSCF6O74JC5JJJYK","download_json":"https://pith.science/pith/IEJNU326MCSSCF6O74JC5JJJYK.json","view_paper":"https://pith.science/paper/IEJNU326","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06673&json=true","fetch_graph":"https://pith.science/api/pith-number/IEJNU326MCSSCF6O74JC5JJJYK/graph.json","fetch_events":"https://pith.science/api/pith-number/IEJNU326MCSSCF6O74JC5JJJYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEJNU326MCSSCF6O74JC5JJJYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEJNU326MCSSCF6O74JC5JJJYK/action/storage_attestation","attest_author":"https://pith.science/pith/IEJNU326MCSSCF6O74JC5JJJYK/action/author_attestation","sign_citation":"https://pith.science/pith/IEJNU326MCSSCF6O74JC5JJJYK/action/citation_signature","submit_replication":"https://pith.science/pith/IEJNU326MCSSCF6O74JC5JJJYK/action/replication_record"}},"created_at":"2026-07-05T07:11:43.640890+00:00","updated_at":"2026-07-05T07:11:43.640890+00:00"}