{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JTK27P6ZUMAZCXP7R66YDPQ6SX","short_pith_number":"pith:JTK27P6Z","canonical_record":{"source":{"id":"1806.01825","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-05T17:31:02Z","cross_cats_sorted":[],"title_canon_sha256":"08635e9d0c8c9ad5cffea6177bd03c425412de49c48484122c4c99e1eb1eb177","abstract_canon_sha256":"636daf385ef3cd6270b2cf7c616fb989f47bfc8552849b9129f52f0d72a5a063"},"schema_version":"1.0"},"canonical_sha256":"4cd5afbfd9a301915dff8fbd81be1e95e8f02de03fd51b6769b4f48439284c5d","source":{"kind":"arxiv","id":"1806.01825","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.01825","created_at":"2026-05-17T23:49:57Z"},{"alias_kind":"arxiv_version","alias_value":"1806.01825v3","created_at":"2026-05-17T23:49:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01825","created_at":"2026-05-17T23:49:57Z"},{"alias_kind":"pith_short_12","alias_value":"JTK27P6ZUMAZ","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JTK27P6ZUMAZCXP7","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JTK27P6Z","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JTK27P6ZUMAZCXP7R66YDPQ6SX","target":"record","payload":{"canonical_record":{"source":{"id":"1806.01825","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-05T17:31:02Z","cross_cats_sorted":[],"title_canon_sha256":"08635e9d0c8c9ad5cffea6177bd03c425412de49c48484122c4c99e1eb1eb177","abstract_canon_sha256":"636daf385ef3cd6270b2cf7c616fb989f47bfc8552849b9129f52f0d72a5a063"},"schema_version":"1.0"},"canonical_sha256":"4cd5afbfd9a301915dff8fbd81be1e95e8f02de03fd51b6769b4f48439284c5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:57.231419Z","signature_b64":"uXavMwPJNjYOitl7yCNKkM8oAtAsfKKvk40FOtVuF9GJAPYYJ1o+o0VoRP3zbWuBB/UNHqEaeodwTcbmvNOBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cd5afbfd9a301915dff8fbd81be1e95e8f02de03fd51b6769b4f48439284c5d","last_reissued_at":"2026-05-17T23:49:57.230647Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:57.230647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.01825","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:49:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VV3y/qF8DY8VCNdjV1x7/UipGNwVpGx8oLvblQxzLjJsN+Z8Mfo4JcgffgjjP5jjY+tE21ETwED8blhZyMklCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:01:54.821930Z"},"content_sha256":"b559f025c71c8029491fa6a6542cea8cd97e52e20128a0aad9fd03ab7de1dca3","schema_version":"1.0","event_id":"sha256:b559f025c71c8029491fa6a6542cea8cd97e52e20128a0aad9fd03ab7de1dca3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JTK27P6ZUMAZCXP7R66YDPQ6SX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Effect of Planning Shape on Dyna-style Planning in High-dimensional State Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Erin J. Talvitie, G. Zacharias Holland, Michael Bowling","submitted_at":"2018-06-05T17:31:02Z","abstract_excerpt":"Dyna is a fundamental approach to model-based reinforcement learning (MBRL) that interleaves planning, acting, and learning in an online setting. In the most typical application of Dyna, the dynamics model is used to generate one-step transitions from selected start states from the agent's history, which are used to update the agent's value function or policy as if they were real experiences. In this work, one-step Dyna was applied to several games from the Arcade Learning Environment (ALE). We found that the model-based updates offered surprisingly little benefit over simply performing more u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01825","kind":"arxiv","version":3},"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":"2026-05-17T23:49:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCMg1IGsWQwpoNjcRYARebKh5M4DYuUadWz8yP2aJspyAU0ijGfxq0CSSKOixAYvWUgTN60G03XQGU+XCI+pAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:01:54.822641Z"},"content_sha256":"37b85f653953b237ecfceb84606e51cfef92008e4940ca80fc5cb8a9d59f5554","schema_version":"1.0","event_id":"sha256:37b85f653953b237ecfceb84606e51cfef92008e4940ca80fc5cb8a9d59f5554"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JTK27P6ZUMAZCXP7R66YDPQ6SX/bundle.json","state_url":"https://pith.science/pith/JTK27P6ZUMAZCXP7R66YDPQ6SX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JTK27P6ZUMAZCXP7R66YDPQ6SX/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":"2026-05-26T06:01:54Z","links":{"resolver":"https://pith.science/pith/JTK27P6ZUMAZCXP7R66YDPQ6SX","bundle":"https://pith.science/pith/JTK27P6ZUMAZCXP7R66YDPQ6SX/bundle.json","state":"https://pith.science/pith/JTK27P6ZUMAZCXP7R66YDPQ6SX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JTK27P6ZUMAZCXP7R66YDPQ6SX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JTK27P6ZUMAZCXP7R66YDPQ6SX","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":"636daf385ef3cd6270b2cf7c616fb989f47bfc8552849b9129f52f0d72a5a063","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-05T17:31:02Z","title_canon_sha256":"08635e9d0c8c9ad5cffea6177bd03c425412de49c48484122c4c99e1eb1eb177"},"schema_version":"1.0","source":{"id":"1806.01825","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.01825","created_at":"2026-05-17T23:49:57Z"},{"alias_kind":"arxiv_version","alias_value":"1806.01825v3","created_at":"2026-05-17T23:49:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01825","created_at":"2026-05-17T23:49:57Z"},{"alias_kind":"pith_short_12","alias_value":"JTK27P6ZUMAZ","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JTK27P6ZUMAZCXP7","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JTK27P6Z","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:37b85f653953b237ecfceb84606e51cfef92008e4940ca80fc5cb8a9d59f5554","target":"graph","created_at":"2026-05-17T23:49:57Z","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":"Dyna is a fundamental approach to model-based reinforcement learning (MBRL) that interleaves planning, acting, and learning in an online setting. In the most typical application of Dyna, the dynamics model is used to generate one-step transitions from selected start states from the agent's history, which are used to update the agent's value function or policy as if they were real experiences. In this work, one-step Dyna was applied to several games from the Arcade Learning Environment (ALE). We found that the model-based updates offered surprisingly little benefit over simply performing more u","authors_text":"Erin J. Talvitie, G. Zacharias Holland, Michael Bowling","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-05T17:31:02Z","title":"The Effect of Planning Shape on Dyna-style Planning in High-dimensional State Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01825","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:b559f025c71c8029491fa6a6542cea8cd97e52e20128a0aad9fd03ab7de1dca3","target":"record","created_at":"2026-05-17T23:49:57Z","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":"636daf385ef3cd6270b2cf7c616fb989f47bfc8552849b9129f52f0d72a5a063","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-05T17:31:02Z","title_canon_sha256":"08635e9d0c8c9ad5cffea6177bd03c425412de49c48484122c4c99e1eb1eb177"},"schema_version":"1.0","source":{"id":"1806.01825","kind":"arxiv","version":3}},"canonical_sha256":"4cd5afbfd9a301915dff8fbd81be1e95e8f02de03fd51b6769b4f48439284c5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cd5afbfd9a301915dff8fbd81be1e95e8f02de03fd51b6769b4f48439284c5d","first_computed_at":"2026-05-17T23:49:57.230647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:57.230647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uXavMwPJNjYOitl7yCNKkM8oAtAsfKKvk40FOtVuF9GJAPYYJ1o+o0VoRP3zbWuBB/UNHqEaeodwTcbmvNOBBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:57.231419Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.01825","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b559f025c71c8029491fa6a6542cea8cd97e52e20128a0aad9fd03ab7de1dca3","sha256:37b85f653953b237ecfceb84606e51cfef92008e4940ca80fc5cb8a9d59f5554"],"state_sha256":"6b1d4fc8fee2bdc053caf1f6fa194a164f0c5b769afb468532e8451d90105683"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4NPzmVcXtlMKn9PkknTkFe3JcTfilU4jR+I2xfHsi0BC/bPLM/M9X/knkALYGcjfJP1Wp3OcjEhVpOUo+7//Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T06:01:54.826653Z","bundle_sha256":"fb86b5b6ff6fa0f4d50f5aa314f6a9426ab0b1186eb2dd36a6aae96c61ae0ae6"}}