{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:JOVSB52AP72GEYUMVJCHCZYUD4","short_pith_number":"pith:JOVSB52A","schema_version":"1.0","canonical_sha256":"4bab20f7407ff462628caa447167141f144b49ae921dd58fb4f77cc35e6e781c","source":{"kind":"arxiv","id":"1612.05159","version":2},"attestation_state":"computed","paper":{"title":"Separation of Concerns in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Harm van Seijen, Joshua Romoff, Mehdi Fatemi, Romain Laroche","submitted_at":"2016-12-15T17:41:41Z","abstract_excerpt":"In this paper, we propose a framework for solving a single-agent task by using multiple agents, each focusing on different aspects of the task. This approach has two main advantages: 1) it allows for training specialized agents on different parts of the task, and 2) it provides a new way to transfer knowledge, by transferring trained agents. Our framework generalizes the traditional hierarchical decomposition, in which, at any moment in time, a single agent has control until it has solved its particular subtask. We illustrate our framework with empirical experiments on two domains."},"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":"1612.05159","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-15T17:41:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"193094977f20adf65da886df3839ca4b779f7e1b76b9306501635937c7c6e8db","abstract_canon_sha256":"9f7775a201b705d5bc8d36ffb7766ca36f84a827eda6a0acae1e7f8d01d263c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:42.296549Z","signature_b64":"YYDWMpynfSd4XEGmVD7HN5KnBtFRIsfjfk+3ouF4NI1/1mjQ62Zz8s36WuJvIl40mW35okAJ1oGxKM5Yrl8rAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bab20f7407ff462628caa447167141f144b49ae921dd58fb4f77cc35e6e781c","last_reissued_at":"2026-05-18T00:47:42.295819Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:42.295819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Separation of Concerns in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Harm van Seijen, Joshua Romoff, Mehdi Fatemi, Romain Laroche","submitted_at":"2016-12-15T17:41:41Z","abstract_excerpt":"In this paper, we propose a framework for solving a single-agent task by using multiple agents, each focusing on different aspects of the task. This approach has two main advantages: 1) it allows for training specialized agents on different parts of the task, and 2) it provides a new way to transfer knowledge, by transferring trained agents. Our framework generalizes the traditional hierarchical decomposition, in which, at any moment in time, a single agent has control until it has solved its particular subtask. We illustrate our framework with empirical experiments on two domains."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.05159","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":""},"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":"1612.05159","created_at":"2026-05-18T00:47:42.295960+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.05159v2","created_at":"2026-05-18T00:47:42.295960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.05159","created_at":"2026-05-18T00:47:42.295960+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOVSB52AP72G","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOVSB52AP72GEYUM","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOVSB52A","created_at":"2026-05-18T12:30:25.849896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.00884","citing_title":"On mechanisms for transfer using landmark value functions in multi-task lifelong reinforcement learning","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOVSB52AP72GEYUMVJCHCZYUD4","json":"https://pith.science/pith/JOVSB52AP72GEYUMVJCHCZYUD4.json","graph_json":"https://pith.science/api/pith-number/JOVSB52AP72GEYUMVJCHCZYUD4/graph.json","events_json":"https://pith.science/api/pith-number/JOVSB52AP72GEYUMVJCHCZYUD4/events.json","paper":"https://pith.science/paper/JOVSB52A"},"agent_actions":{"view_html":"https://pith.science/pith/JOVSB52AP72GEYUMVJCHCZYUD4","download_json":"https://pith.science/pith/JOVSB52AP72GEYUMVJCHCZYUD4.json","view_paper":"https://pith.science/paper/JOVSB52A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.05159&json=true","fetch_graph":"https://pith.science/api/pith-number/JOVSB52AP72GEYUMVJCHCZYUD4/graph.json","fetch_events":"https://pith.science/api/pith-number/JOVSB52AP72GEYUMVJCHCZYUD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOVSB52AP72GEYUMVJCHCZYUD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOVSB52AP72GEYUMVJCHCZYUD4/action/storage_attestation","attest_author":"https://pith.science/pith/JOVSB52AP72GEYUMVJCHCZYUD4/action/author_attestation","sign_citation":"https://pith.science/pith/JOVSB52AP72GEYUMVJCHCZYUD4/action/citation_signature","submit_replication":"https://pith.science/pith/JOVSB52AP72GEYUMVJCHCZYUD4/action/replication_record"}},"created_at":"2026-05-18T00:47:42.295960+00:00","updated_at":"2026-05-18T00:47:42.295960+00:00"}