{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QGD34IOTX3BJLRHPA2OFLDUEN3","short_pith_number":"pith:QGD34IOT","canonical_record":{"source":{"id":"2002.05822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-14T00:27:58Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"eab052847a1777b84b8067c2586103dd0f0ffb11f1fb64b643be3fcdb68662bb","abstract_canon_sha256":"b17ee801a3db1c86ed5e498474e16db41e0645970df8722b1b094c6c746bbf79"},"schema_version":"1.0"},"canonical_sha256":"8187be21d3bec295c4ef069c558e846ed8baa5d6a9ee6eaf5bb497019c330ab4","source":{"kind":"arxiv","id":"2002.05822","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.05822","created_at":"2026-07-05T00:40:36Z"},{"alias_kind":"arxiv_version","alias_value":"2002.05822v1","created_at":"2026-07-05T00:40:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05822","created_at":"2026-07-05T00:40:36Z"},{"alias_kind":"pith_short_12","alias_value":"QGD34IOTX3BJ","created_at":"2026-07-05T00:40:36Z"},{"alias_kind":"pith_short_16","alias_value":"QGD34IOTX3BJLRHP","created_at":"2026-07-05T00:40:36Z"},{"alias_kind":"pith_short_8","alias_value":"QGD34IOT","created_at":"2026-07-05T00:40:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QGD34IOTX3BJLRHPA2OFLDUEN3","target":"record","payload":{"canonical_record":{"source":{"id":"2002.05822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-14T00:27:58Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"eab052847a1777b84b8067c2586103dd0f0ffb11f1fb64b643be3fcdb68662bb","abstract_canon_sha256":"b17ee801a3db1c86ed5e498474e16db41e0645970df8722b1b094c6c746bbf79"},"schema_version":"1.0"},"canonical_sha256":"8187be21d3bec295c4ef069c558e846ed8baa5d6a9ee6eaf5bb497019c330ab4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:36.353663Z","signature_b64":"7kBWqe21ikfkvKcvnUupeMQhsr7s7DQCRm1wesYhv+aw/gUlSK7i2t3vBrPTORV3LXZBr2gV1UL6QXF0Hn4eCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8187be21d3bec295c4ef069c558e846ed8baa5d6a9ee6eaf5bb497019c330ab4","last_reissued_at":"2026-07-05T00:40:36.353213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:36.353213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.05822","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":"2026-07-05T00:40:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NkHmsrQU8lNlH4sKYcgmQX7mKmon/s7SZ3b8BEsT3AlT6wHIhAeTukqfhrVaoct3c1CbtIC8Ua7y/kWx7gGVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:39:18.732110Z"},"content_sha256":"ebff1fff4afa3722cf678d641766ed991af53349fae1541177b25341df2e692c","schema_version":"1.0","event_id":"sha256:ebff1fff4afa3722cf678d641766ed991af53349fae1541177b25341df2e692c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QGD34IOTX3BJLRHPA2OFLDUEN3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Frequency-based Search-control in Dyna","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir-massoud Farahmand, Jincheng Mei, Yangchen Pan","submitted_at":"2020-02-14T00:27:58Z","abstract_excerpt":"Model-based reinforcement learning has been empirically demonstrated as a successful strategy to improve sample efficiency. In particular, Dyna is an elegant model-based architecture integrating learning and planning that provides huge flexibility of using a model. One of the most important components in Dyna is called search-control, which refers to the process of generating state or state-action pairs from which we query the model to acquire simulated experiences. Search-control is critical in improving learning efficiency. In this work, we propose a simple and novel search-control strategy "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05822","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/2002.05822/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:40:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qBUhCNZjtQmWFpsoG1f0sL/1bndcaQ89UVGVpC4GUHKF+KVgeEszDV9BisbhZZQBdWlkLbeddkQxjOuqaYaGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:39:18.732742Z"},"content_sha256":"560df1fd78c33a77c8ba325a503d1bf56c61c29a5656cdb15a28efe480362163","schema_version":"1.0","event_id":"sha256:560df1fd78c33a77c8ba325a503d1bf56c61c29a5656cdb15a28efe480362163"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QGD34IOTX3BJLRHPA2OFLDUEN3/bundle.json","state_url":"https://pith.science/pith/QGD34IOTX3BJLRHPA2OFLDUEN3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QGD34IOTX3BJLRHPA2OFLDUEN3/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":"2026-07-07T04:39:18Z","links":{"resolver":"https://pith.science/pith/QGD34IOTX3BJLRHPA2OFLDUEN3","bundle":"https://pith.science/pith/QGD34IOTX3BJLRHPA2OFLDUEN3/bundle.json","state":"https://pith.science/pith/QGD34IOTX3BJLRHPA2OFLDUEN3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QGD34IOTX3BJLRHPA2OFLDUEN3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QGD34IOTX3BJLRHPA2OFLDUEN3","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":"b17ee801a3db1c86ed5e498474e16db41e0645970df8722b1b094c6c746bbf79","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-14T00:27:58Z","title_canon_sha256":"eab052847a1777b84b8067c2586103dd0f0ffb11f1fb64b643be3fcdb68662bb"},"schema_version":"1.0","source":{"id":"2002.05822","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.05822","created_at":"2026-07-05T00:40:36Z"},{"alias_kind":"arxiv_version","alias_value":"2002.05822v1","created_at":"2026-07-05T00:40:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05822","created_at":"2026-07-05T00:40:36Z"},{"alias_kind":"pith_short_12","alias_value":"QGD34IOTX3BJ","created_at":"2026-07-05T00:40:36Z"},{"alias_kind":"pith_short_16","alias_value":"QGD34IOTX3BJLRHP","created_at":"2026-07-05T00:40:36Z"},{"alias_kind":"pith_short_8","alias_value":"QGD34IOT","created_at":"2026-07-05T00:40:36Z"}],"graph_snapshots":[{"event_id":"sha256:560df1fd78c33a77c8ba325a503d1bf56c61c29a5656cdb15a28efe480362163","target":"graph","created_at":"2026-07-05T00:40:36Z","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/2002.05822/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning has been empirically demonstrated as a successful strategy to improve sample efficiency. In particular, Dyna is an elegant model-based architecture integrating learning and planning that provides huge flexibility of using a model. One of the most important components in Dyna is called search-control, which refers to the process of generating state or state-action pairs from which we query the model to acquire simulated experiences. Search-control is critical in improving learning efficiency. In this work, we propose a simple and novel search-control strategy ","authors_text":"Amir-massoud Farahmand, Jincheng Mei, Yangchen Pan","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-14T00:27:58Z","title":"Frequency-based Search-control in Dyna"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05822","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:ebff1fff4afa3722cf678d641766ed991af53349fae1541177b25341df2e692c","target":"record","created_at":"2026-07-05T00:40:36Z","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":"b17ee801a3db1c86ed5e498474e16db41e0645970df8722b1b094c6c746bbf79","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-14T00:27:58Z","title_canon_sha256":"eab052847a1777b84b8067c2586103dd0f0ffb11f1fb64b643be3fcdb68662bb"},"schema_version":"1.0","source":{"id":"2002.05822","kind":"arxiv","version":1}},"canonical_sha256":"8187be21d3bec295c4ef069c558e846ed8baa5d6a9ee6eaf5bb497019c330ab4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8187be21d3bec295c4ef069c558e846ed8baa5d6a9ee6eaf5bb497019c330ab4","first_computed_at":"2026-07-05T00:40:36.353213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:36.353213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7kBWqe21ikfkvKcvnUupeMQhsr7s7DQCRm1wesYhv+aw/gUlSK7i2t3vBrPTORV3LXZBr2gV1UL6QXF0Hn4eCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:36.353663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.05822","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebff1fff4afa3722cf678d641766ed991af53349fae1541177b25341df2e692c","sha256:560df1fd78c33a77c8ba325a503d1bf56c61c29a5656cdb15a28efe480362163"],"state_sha256":"03c51452e89ea342d8f36290a5bfed6972fadd6b22d16ec457a6d1618fcc87de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NdscPBZsQnVDOkl6OlVcfIClcPT+bM7kRQnKg7CSFp21h7yJsUVnq6mJfv4FwUY8za19UqvuOuq9dfWuha6HCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:39:18.735891Z","bundle_sha256":"e6bf6326b2db1f90010efa6b5e8511440aa912a78eeb42f5bf3f389243622c72"}}