{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FCOCMVWRUOJBIJMPKFHUSNNCBX","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":"5dfb4e3e99019de9ca849e77ad9bd5cc7b0d3e146605885790b6e23db322c100","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-23T03:22:01Z","title_canon_sha256":"e689854413c7a801459905389fd3c48b5d1a49565db3a61f92ce1708fb524397"},"schema_version":"1.0","source":{"id":"2010.12142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12142","created_at":"2026-07-05T01:45:34Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12142v1","created_at":"2026-07-05T01:45:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12142","created_at":"2026-07-05T01:45:34Z"},{"alias_kind":"pith_short_12","alias_value":"FCOCMVWRUOJB","created_at":"2026-07-05T01:45:34Z"},{"alias_kind":"pith_short_16","alias_value":"FCOCMVWRUOJBIJMP","created_at":"2026-07-05T01:45:34Z"},{"alias_kind":"pith_short_8","alias_value":"FCOCMVWR","created_at":"2026-07-05T01:45:34Z"}],"graph_snapshots":[{"event_id":"sha256:dfe85a6a9af5b54f5a87dff4cce7fcc38af0f598566b2dca2b538af4a7ddc5e6","target":"graph","created_at":"2026-07-05T01:45:34Z","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/2010.12142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sample efficiency has been one of the major challenges for deep reinforcement learning. Recently, model-based reinforcement learning has been proposed to address this challenge by performing planning on imaginary trajectories with a learned world model. However, world model learning may suffer from overfitting to training trajectories, and thus model-based value estimation and policy search will be pone to be sucked in an inferior local policy. In this paper, we propose a novel model-based reinforcement learning algorithm, called BrIdging Reality and Dream (BIRD). It maximizes the mutual infor","authors_text":"Chongjie Zhang, Guangxiang Zhu, Honglak Lee, Minghao Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-23T03:22:01Z","title":"Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12142","kind":"arxiv","version":1},"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":"sha256:304fb4f5f144e770a8a9985f2b62ccc707a405dfaa41e071a51e4990234d3252","target":"record","created_at":"2026-07-05T01:45:34Z","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":"5dfb4e3e99019de9ca849e77ad9bd5cc7b0d3e146605885790b6e23db322c100","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-23T03:22:01Z","title_canon_sha256":"e689854413c7a801459905389fd3c48b5d1a49565db3a61f92ce1708fb524397"},"schema_version":"1.0","source":{"id":"2010.12142","kind":"arxiv","version":1}},"canonical_sha256":"289c2656d1a39214258f514f4935a20df5f5e4f3d54c548acd64172ae7d4bf7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"289c2656d1a39214258f514f4935a20df5f5e4f3d54c548acd64172ae7d4bf7b","first_computed_at":"2026-07-05T01:45:34.210288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:34.210288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wlbo+p83hBCRn5bW4yvmorQQDTN+BofS3lBTstF6ScztxAj3WccOaCpm2SczxXlNeLblDY8uqRAdD5cxINwnCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:34.210760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:304fb4f5f144e770a8a9985f2b62ccc707a405dfaa41e071a51e4990234d3252","sha256:dfe85a6a9af5b54f5a87dff4cce7fcc38af0f598566b2dca2b538af4a7ddc5e6"],"state_sha256":"b7792ab90aec30dcd8b9b2938bd86defb061023a826897a3a8aad11241a02939"}