{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RED7FTH27HHHHNUT2LQL2UCCFT","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":"554ec622b2f5dd859e3a47ac978e277f95d488acb02fc8aaee612d3f4185be8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-22T13:19:02Z","title_canon_sha256":"4cb900d91dea91c735a0aca7c3d7f762978761c4e7fecde2d02797e5dcedd11c"},"schema_version":"1.0","source":{"id":"2208.10291","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.10291","created_at":"2026-07-05T05:35:20Z"},{"alias_kind":"arxiv_version","alias_value":"2208.10291v3","created_at":"2026-07-05T05:35:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10291","created_at":"2026-07-05T05:35:20Z"},{"alias_kind":"pith_short_12","alias_value":"RED7FTH27HHH","created_at":"2026-07-05T05:35:20Z"},{"alias_kind":"pith_short_16","alias_value":"RED7FTH27HHHHNUT","created_at":"2026-07-05T05:35:20Z"},{"alias_kind":"pith_short_8","alias_value":"RED7FTH2","created_at":"2026-07-05T05:35:20Z"}],"graph_snapshots":[{"event_id":"sha256:cd8580e8d990fd9679372254d6cb401eec0091a6bfcb4e2cc516a51d1c001331","target":"graph","created_at":"2026-07-05T05:35:20Z","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/2208.10291/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Planning-based reinforcement learning has shown strong performance in tasks in discrete and low-dimensional continuous action spaces. However, planning usually brings significant computational overhead for decision-making, and scaling such methods to high-dimensional action spaces remains challenging. To advance efficient planning for high-dimensional continuous control, we propose Trajectory Autoencoding Planner (TAP), which learns low-dimensional latent action codes with a state-conditional VQ-VAE. The decoder of the VQ-VAE thus serves as a novel dynamics model that takes latent actions and ","authors_text":"Edward Grefenstette, Michael Janner, Tianjun Zhang, Tim Rockt\\\"aschel, Yuandong Tian, Yueying Li, Zhengyao Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-22T13:19:02Z","title":"Efficient Planning in a Compact Latent Action Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10291","kind":"arxiv","version":3},"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":"sha256:69a1409b58582227320cedd92d10dc05f9dc6b4f79a1a5b18e4e3996dc1df4b5","target":"record","created_at":"2026-07-05T05:35:20Z","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":"554ec622b2f5dd859e3a47ac978e277f95d488acb02fc8aaee612d3f4185be8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-22T13:19:02Z","title_canon_sha256":"4cb900d91dea91c735a0aca7c3d7f762978761c4e7fecde2d02797e5dcedd11c"},"schema_version":"1.0","source":{"id":"2208.10291","kind":"arxiv","version":3}},"canonical_sha256":"8907f2ccfaf9ce73b693d2e0bd50422cf290a7b1e5ff80a613b75774e3a7600c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8907f2ccfaf9ce73b693d2e0bd50422cf290a7b1e5ff80a613b75774e3a7600c","first_computed_at":"2026-07-05T05:35:20.143407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:35:20.143407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fQazVNAPS2efQwoHmrN8gXeM7RITTIcDwhyjNK5A4RJQrFNu/0NcnKqw1GoItW53pTjlYST1jGdM6BzqqLmaBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:35:20.143928Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.10291","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69a1409b58582227320cedd92d10dc05f9dc6b4f79a1a5b18e4e3996dc1df4b5","sha256:cd8580e8d990fd9679372254d6cb401eec0091a6bfcb4e2cc516a51d1c001331"],"state_sha256":"d2edfe9f4a4206de413e454b2041ee8dd143586ee0faabbe9d4df1e0be13ce3c"}