{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7QBHQVIQ2BFJPULTXDWXEDERZX","short_pith_number":"pith:7QBHQVIQ","schema_version":"1.0","canonical_sha256":"fc02785510d04a97d173b8ed720c91cdcbc67cb843519143df0cea54e83b65ba","source":{"kind":"arxiv","id":"2309.14243","version":2},"attestation_state":"computed","paper":{"title":"Enhancing data efficiency in reinforcement learning: a novel imagination mechanism based on mesh information propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Maowei Jiang, Zihang Wang","submitted_at":"2023-09-25T16:03:08Z","abstract_excerpt":"Reinforcement learning(RL) algorithms face the challenge of limited data efficiency, particularly when dealing with high-dimensional state spaces and large-scale problems. Most of RL methods often rely solely on state transition information within the same episode when updating the agent's Critic, which can lead to low data efficiency and sub-optimal training time consumption. Inspired by human-like analogical reasoning abilities, we introduce a novel mesh information propagation mechanism, termed the 'Imagination Mechanism (IM)', designed to significantly enhance the data efficiency of RL alg"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.14243","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-25T16:03:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d82f24eaec4c3676275ac9e0bb20061e4260f9e0cf543f54935f16e1f1873fd7","abstract_canon_sha256":"a0525ffde12abb89343a22e271aa443a5ddc16f441b20a3b38697843dda7aacf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:55.319084Z","signature_b64":"qIA5/U6sMY7Y7Xp8V9IXLTOEA/k6jnA/Tssi3vKtskO+Ymvq3eF7qhr94BIesDUsnz37IMoI31FJ2wBwVtCgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc02785510d04a97d173b8ed720c91cdcbc67cb843519143df0cea54e83b65ba","last_reissued_at":"2026-07-05T06:54:55.318591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:55.318591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing data efficiency in reinforcement learning: a novel imagination mechanism based on mesh information propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Maowei Jiang, Zihang Wang","submitted_at":"2023-09-25T16:03:08Z","abstract_excerpt":"Reinforcement learning(RL) algorithms face the challenge of limited data efficiency, particularly when dealing with high-dimensional state spaces and large-scale problems. Most of RL methods often rely solely on state transition information within the same episode when updating the agent's Critic, which can lead to low data efficiency and sub-optimal training time consumption. Inspired by human-like analogical reasoning abilities, we introduce a novel mesh information propagation mechanism, termed the 'Imagination Mechanism (IM)', designed to significantly enhance the data efficiency of RL alg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14243","kind":"arxiv","version":2},"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/2309.14243/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.14243","created_at":"2026-07-05T06:54:55.318655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.14243v2","created_at":"2026-07-05T06:54:55.318655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14243","created_at":"2026-07-05T06:54:55.318655+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QBHQVIQ2BFJ","created_at":"2026-07-05T06:54:55.318655+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QBHQVIQ2BFJPULT","created_at":"2026-07-05T06:54:55.318655+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QBHQVIQ","created_at":"2026-07-05T06:54:55.318655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26333","citing_title":"Mesh-RL: Coupled subgrid reinforcement learning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7QBHQVIQ2BFJPULTXDWXEDERZX","json":"https://pith.science/pith/7QBHQVIQ2BFJPULTXDWXEDERZX.json","graph_json":"https://pith.science/api/pith-number/7QBHQVIQ2BFJPULTXDWXEDERZX/graph.json","events_json":"https://pith.science/api/pith-number/7QBHQVIQ2BFJPULTXDWXEDERZX/events.json","paper":"https://pith.science/paper/7QBHQVIQ"},"agent_actions":{"view_html":"https://pith.science/pith/7QBHQVIQ2BFJPULTXDWXEDERZX","download_json":"https://pith.science/pith/7QBHQVIQ2BFJPULTXDWXEDERZX.json","view_paper":"https://pith.science/paper/7QBHQVIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.14243&json=true","fetch_graph":"https://pith.science/api/pith-number/7QBHQVIQ2BFJPULTXDWXEDERZX/graph.json","fetch_events":"https://pith.science/api/pith-number/7QBHQVIQ2BFJPULTXDWXEDERZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QBHQVIQ2BFJPULTXDWXEDERZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QBHQVIQ2BFJPULTXDWXEDERZX/action/storage_attestation","attest_author":"https://pith.science/pith/7QBHQVIQ2BFJPULTXDWXEDERZX/action/author_attestation","sign_citation":"https://pith.science/pith/7QBHQVIQ2BFJPULTXDWXEDERZX/action/citation_signature","submit_replication":"https://pith.science/pith/7QBHQVIQ2BFJPULTXDWXEDERZX/action/replication_record"}},"created_at":"2026-07-05T06:54:55.318655+00:00","updated_at":"2026-07-05T06:54:55.318655+00:00"}