{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:47TOTDRZVU3UJWZFLC6U3JJTPD","short_pith_number":"pith:47TOTDRZ","schema_version":"1.0","canonical_sha256":"e7e6e98e39ad3744db2558bd4da53378d81af3ffa30cd1d6c6bf8495052c6681","source":{"kind":"arxiv","id":"2307.05209","version":4},"attestation_state":"computed","paper":{"title":"Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Guy Azran, Mohamad H. Danesh, Sarah Keren, Stefano V. Albrecht","submitted_at":"2023-07-11T12:28:05Z","abstract_excerpt":"Recent studies show that deep reinforcement learning (DRL) agents tend to overfit to the task on which they were trained and fail to adapt to minor environment changes. To expedite learning when transferring to unseen tasks, we propose a novel approach to representing the current task using reward machines (RMs), state machine abstractions that induce subtasks based on the current task's rewards and dynamics. Our method provides agents with symbolic representations of optimal transitions from their current abstract state and rewards them for achieving these transitions. These representations a"},"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":"2307.05209","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-11T12:28:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"93a839115aec07b5d7086fd801c37efffa6d81e2203abd9e5d9b8b80b9889f5a","abstract_canon_sha256":"f3e1cb4aa8ff365b7142dce5916f571b7db0eb5e02a00aeea67730aac056d8ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:25.605836Z","signature_b64":"ahGP3rX8QsCPIFoMg8xuLxeKXg8Kb8CE7+NCdViexZ/V1Hh6HrNbNCaIy3rYzLRGvM2rs8oZPhvEtdwRpYmUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7e6e98e39ad3744db2558bd4da53378d81af3ffa30cd1d6c6bf8495052c6681","last_reissued_at":"2026-07-05T07:47:25.605452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:25.605452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Guy Azran, Mohamad H. Danesh, Sarah Keren, Stefano V. Albrecht","submitted_at":"2023-07-11T12:28:05Z","abstract_excerpt":"Recent studies show that deep reinforcement learning (DRL) agents tend to overfit to the task on which they were trained and fail to adapt to minor environment changes. To expedite learning when transferring to unseen tasks, we propose a novel approach to representing the current task using reward machines (RMs), state machine abstractions that induce subtasks based on the current task's rewards and dynamics. Our method provides agents with symbolic representations of optimal transitions from their current abstract state and rewards them for achieving these transitions. These representations a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05209","kind":"arxiv","version":4},"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/2307.05209/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":"2307.05209","created_at":"2026-07-05T07:47:25.605508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.05209v4","created_at":"2026-07-05T07:47:25.605508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05209","created_at":"2026-07-05T07:47:25.605508+00:00"},{"alias_kind":"pith_short_12","alias_value":"47TOTDRZVU3U","created_at":"2026-07-05T07:47:25.605508+00:00"},{"alias_kind":"pith_short_16","alias_value":"47TOTDRZVU3UJWZF","created_at":"2026-07-05T07:47:25.605508+00:00"},{"alias_kind":"pith_short_8","alias_value":"47TOTDRZ","created_at":"2026-07-05T07:47:25.605508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47TOTDRZVU3UJWZFLC6U3JJTPD","json":"https://pith.science/pith/47TOTDRZVU3UJWZFLC6U3JJTPD.json","graph_json":"https://pith.science/api/pith-number/47TOTDRZVU3UJWZFLC6U3JJTPD/graph.json","events_json":"https://pith.science/api/pith-number/47TOTDRZVU3UJWZFLC6U3JJTPD/events.json","paper":"https://pith.science/paper/47TOTDRZ"},"agent_actions":{"view_html":"https://pith.science/pith/47TOTDRZVU3UJWZFLC6U3JJTPD","download_json":"https://pith.science/pith/47TOTDRZVU3UJWZFLC6U3JJTPD.json","view_paper":"https://pith.science/paper/47TOTDRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.05209&json=true","fetch_graph":"https://pith.science/api/pith-number/47TOTDRZVU3UJWZFLC6U3JJTPD/graph.json","fetch_events":"https://pith.science/api/pith-number/47TOTDRZVU3UJWZFLC6U3JJTPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47TOTDRZVU3UJWZFLC6U3JJTPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47TOTDRZVU3UJWZFLC6U3JJTPD/action/storage_attestation","attest_author":"https://pith.science/pith/47TOTDRZVU3UJWZFLC6U3JJTPD/action/author_attestation","sign_citation":"https://pith.science/pith/47TOTDRZVU3UJWZFLC6U3JJTPD/action/citation_signature","submit_replication":"https://pith.science/pith/47TOTDRZVU3UJWZFLC6U3JJTPD/action/replication_record"}},"created_at":"2026-07-05T07:47:25.605508+00:00","updated_at":"2026-07-05T07:47:25.605508+00:00"}