{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6XJV32RBC42TBUO5JV2CB37HIO","short_pith_number":"pith:6XJV32RB","schema_version":"1.0","canonical_sha256":"f5d35dea21173530d1dd4d7420efe7438f051c3fcde1d3f0fdfc220ad8896d51","source":{"kind":"arxiv","id":"1812.00025","version":1},"attestation_state":"computed","paper":{"title":"Modulated Policy Hierarchies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Pashevich, Cordelia Schmid, Danijar Hafner, James Davidson, Rahul Sukthankar","submitted_at":"2018-11-30T19:12:18Z","abstract_excerpt":"Solving tasks with sparse rewards is a main challenge in reinforcement learning. While hierarchical controllers are an intuitive approach to this problem, current methods often require manual reward shaping, alternating training phases, or manually defined sub tasks. We introduce modulated policy hierarchies (MPH), that can learn end-to-end to solve tasks from sparse rewards. To achieve this, we study different modulation signals and exploration for hierarchical controllers. Specifically, we find that communicating via bit-vectors is more efficient than selecting one out of multiple skills, as"},"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":"1812.00025","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-30T19:12:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b12604cefdb7642ff2bc942a0edc0b0f9c9f5bb0a5a293ad1b5b179ad20d06aa","abstract_canon_sha256":"30e068e696ef41f9b7b730959073ac726da28bb0c5cb2a042fc43fb44a18fda3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:27.539277Z","signature_b64":"SKt81BcaNO/b9wCUDAy16li7TYPWz4RFSq4YwZCzrb27j2OZNFqp9bxfTadsUiBOUTTFACDQG4i7KORVUPqZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5d35dea21173530d1dd4d7420efe7438f051c3fcde1d3f0fdfc220ad8896d51","last_reissued_at":"2026-05-17T23:59:27.538542Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:27.538542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modulated Policy Hierarchies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Pashevich, Cordelia Schmid, Danijar Hafner, James Davidson, Rahul Sukthankar","submitted_at":"2018-11-30T19:12:18Z","abstract_excerpt":"Solving tasks with sparse rewards is a main challenge in reinforcement learning. While hierarchical controllers are an intuitive approach to this problem, current methods often require manual reward shaping, alternating training phases, or manually defined sub tasks. We introduce modulated policy hierarchies (MPH), that can learn end-to-end to solve tasks from sparse rewards. To achieve this, we study different modulation signals and exploration for hierarchical controllers. Specifically, we find that communicating via bit-vectors is more efficient than selecting one out of multiple skills, as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00025","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":""},"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":"1812.00025","created_at":"2026-05-17T23:59:27.538654+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.00025v1","created_at":"2026-05-17T23:59:27.538654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00025","created_at":"2026-05-17T23:59:27.538654+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XJV32RBC42T","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XJV32RBC42TBUO5","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XJV32RB","created_at":"2026-05-18T12:32:11.075285+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/6XJV32RBC42TBUO5JV2CB37HIO","json":"https://pith.science/pith/6XJV32RBC42TBUO5JV2CB37HIO.json","graph_json":"https://pith.science/api/pith-number/6XJV32RBC42TBUO5JV2CB37HIO/graph.json","events_json":"https://pith.science/api/pith-number/6XJV32RBC42TBUO5JV2CB37HIO/events.json","paper":"https://pith.science/paper/6XJV32RB"},"agent_actions":{"view_html":"https://pith.science/pith/6XJV32RBC42TBUO5JV2CB37HIO","download_json":"https://pith.science/pith/6XJV32RBC42TBUO5JV2CB37HIO.json","view_paper":"https://pith.science/paper/6XJV32RB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.00025&json=true","fetch_graph":"https://pith.science/api/pith-number/6XJV32RBC42TBUO5JV2CB37HIO/graph.json","fetch_events":"https://pith.science/api/pith-number/6XJV32RBC42TBUO5JV2CB37HIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XJV32RBC42TBUO5JV2CB37HIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XJV32RBC42TBUO5JV2CB37HIO/action/storage_attestation","attest_author":"https://pith.science/pith/6XJV32RBC42TBUO5JV2CB37HIO/action/author_attestation","sign_citation":"https://pith.science/pith/6XJV32RBC42TBUO5JV2CB37HIO/action/citation_signature","submit_replication":"https://pith.science/pith/6XJV32RBC42TBUO5JV2CB37HIO/action/replication_record"}},"created_at":"2026-05-17T23:59:27.538654+00:00","updated_at":"2026-05-17T23:59:27.538654+00:00"}