{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NYJHYOBHRMMFFKMF4TBTXX7HSA","short_pith_number":"pith:NYJHYOBH","canonical_record":{"source":{"id":"1906.08649","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-20T14:13:12Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"18b1fcedcb4cd2060009a4fb7d56fc6aa95e6320e1dffca00c457e68419b2ac6","abstract_canon_sha256":"116d9583a5a50d5bcd891c570bf58631d190b2058f294346da5c01e0a9f20cb6"},"schema_version":"1.0"},"canonical_sha256":"6e127c38278b1852a985e4c33bdfe79000b42e9cd7329866c94cb9c80d21219c","source":{"kind":"arxiv","id":"1906.08649","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08649","created_at":"2026-05-17T23:42:49Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08649v1","created_at":"2026-05-17T23:42:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08649","created_at":"2026-05-17T23:42:49Z"},{"alias_kind":"pith_short_12","alias_value":"NYJHYOBHRMMF","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NYJHYOBHRMMFFKMF","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NYJHYOBH","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NYJHYOBHRMMFFKMF4TBTXX7HSA","target":"record","payload":{"canonical_record":{"source":{"id":"1906.08649","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-20T14:13:12Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"18b1fcedcb4cd2060009a4fb7d56fc6aa95e6320e1dffca00c457e68419b2ac6","abstract_canon_sha256":"116d9583a5a50d5bcd891c570bf58631d190b2058f294346da5c01e0a9f20cb6"},"schema_version":"1.0"},"canonical_sha256":"6e127c38278b1852a985e4c33bdfe79000b42e9cd7329866c94cb9c80d21219c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:49.977824Z","signature_b64":"Ls0Hfr3MkzFOBpiLSfps7lQHh+eohBRKe9ki3q6YBsx+A0rXaWEVSiYqKnzsEzqLDpoYtfqrgmzKbu/LbgwQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e127c38278b1852a985e4c33bdfe79000b42e9cd7329866c94cb9c80d21219c","last_reissued_at":"2026-05-17T23:42:49.977442Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:49.977442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.08649","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6INwbB1G/WkmhI1jn4QVRARCsgSO7GAQK6avQt1iY+XzTEwKbA1nvFNXU4Iovpuc7/4Oc9uoWUqpDXOyUKsTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:41:22.349306Z"},"content_sha256":"8ba1cdbf272daa2814fa829d73bf6b4949907de350113d9770ebb0436ecf5c03","schema_version":"1.0","event_id":"sha256:8ba1cdbf272daa2814fa829d73bf6b4949907de350113d9770ebb0436ecf5c03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NYJHYOBHRMMFFKMF4TBTXX7HSA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Model-based Planning with Policy Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jimmy Ba, Tingwu Wang","submitted_at":"2019-06-20T14:13:12Z","abstract_excerpt":"Model-based reinforcement learning (MBRL) with model-predictive control or online planning has shown great potential for locomotion control tasks in terms of both sample efficiency and asymptotic performance. Despite their initial successes, the existing planning methods search from candidate sequences randomly generated in the action space, which is inefficient in complex high-dimensional environments. In this paper, we propose a novel MBRL algorithm, model-based policy planning (POPLIN), that combines policy networks with online planning. More specifically, we formulate action planning at ea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08649","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2FQH9KgfE5oSuuNthEgXauIdwcFRykljqvtlEEqG9NqVqzpeGUBEb+lMJ+J8VHgm76JF5apPUKyfIYYZnEMKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:41:22.351909Z"},"content_sha256":"f864e1473ad0344ab80ee89732aafca7f2d09dca1b297eb18ae26c6ac4c6204e","schema_version":"1.0","event_id":"sha256:f864e1473ad0344ab80ee89732aafca7f2d09dca1b297eb18ae26c6ac4c6204e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NYJHYOBHRMMFFKMF4TBTXX7HSA/bundle.json","state_url":"https://pith.science/pith/NYJHYOBHRMMFFKMF4TBTXX7HSA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NYJHYOBHRMMFFKMF4TBTXX7HSA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T16:41:22Z","links":{"resolver":"https://pith.science/pith/NYJHYOBHRMMFFKMF4TBTXX7HSA","bundle":"https://pith.science/pith/NYJHYOBHRMMFFKMF4TBTXX7HSA/bundle.json","state":"https://pith.science/pith/NYJHYOBHRMMFFKMF4TBTXX7HSA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NYJHYOBHRMMFFKMF4TBTXX7HSA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NYJHYOBHRMMFFKMF4TBTXX7HSA","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":"116d9583a5a50d5bcd891c570bf58631d190b2058f294346da5c01e0a9f20cb6","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-20T14:13:12Z","title_canon_sha256":"18b1fcedcb4cd2060009a4fb7d56fc6aa95e6320e1dffca00c457e68419b2ac6"},"schema_version":"1.0","source":{"id":"1906.08649","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08649","created_at":"2026-05-17T23:42:49Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08649v1","created_at":"2026-05-17T23:42:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08649","created_at":"2026-05-17T23:42:49Z"},{"alias_kind":"pith_short_12","alias_value":"NYJHYOBHRMMF","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NYJHYOBHRMMFFKMF","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NYJHYOBH","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:f864e1473ad0344ab80ee89732aafca7f2d09dca1b297eb18ae26c6ac4c6204e","target":"graph","created_at":"2026-05-17T23:42:49Z","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":"Model-based reinforcement learning (MBRL) with model-predictive control or online planning has shown great potential for locomotion control tasks in terms of both sample efficiency and asymptotic performance. Despite their initial successes, the existing planning methods search from candidate sequences randomly generated in the action space, which is inefficient in complex high-dimensional environments. In this paper, we propose a novel MBRL algorithm, model-based policy planning (POPLIN), that combines policy networks with online planning. More specifically, we formulate action planning at ea","authors_text":"Jimmy Ba, Tingwu Wang","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-20T14:13:12Z","title":"Exploring Model-based Planning with Policy Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08649","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":"sha256:8ba1cdbf272daa2814fa829d73bf6b4949907de350113d9770ebb0436ecf5c03","target":"record","created_at":"2026-05-17T23:42:49Z","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":"116d9583a5a50d5bcd891c570bf58631d190b2058f294346da5c01e0a9f20cb6","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-20T14:13:12Z","title_canon_sha256":"18b1fcedcb4cd2060009a4fb7d56fc6aa95e6320e1dffca00c457e68419b2ac6"},"schema_version":"1.0","source":{"id":"1906.08649","kind":"arxiv","version":1}},"canonical_sha256":"6e127c38278b1852a985e4c33bdfe79000b42e9cd7329866c94cb9c80d21219c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e127c38278b1852a985e4c33bdfe79000b42e9cd7329866c94cb9c80d21219c","first_computed_at":"2026-05-17T23:42:49.977442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:49.977442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ls0Hfr3MkzFOBpiLSfps7lQHh+eohBRKe9ki3q6YBsx+A0rXaWEVSiYqKnzsEzqLDpoYtfqrgmzKbu/LbgwQCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:49.977824Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.08649","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ba1cdbf272daa2814fa829d73bf6b4949907de350113d9770ebb0436ecf5c03","sha256:f864e1473ad0344ab80ee89732aafca7f2d09dca1b297eb18ae26c6ac4c6204e"],"state_sha256":"bab6bfd861e7fa6f14cf136ef166b4651c69bc5b3543babfb53f2eb5edcc1b82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z7asYo51cP61pjK/cQrEUMcEWDvJrc58m4sPdJWxroV7VgKrfsmu5E6r/LDph9Vxv+b6rTQhptYJ2naogkc1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:41:22.360195Z","bundle_sha256":"229210a85ee308905b061e2ec913a9fd11101ac6fc39cf9e65094f304d40976a"}}