{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XLK6NALVOLK7R47PB4NX6VN4LE","short_pith_number":"pith:XLK6NALV","schema_version":"1.0","canonical_sha256":"bad5e6817572d5f8f3ef0f1b7f55bc59043453f88f35a40f053bd4cc05a1e75c","source":{"kind":"arxiv","id":"1809.06146","version":2},"attestation_state":"computed","paper":{"title":"Curriculum goal masking for continuous deep reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Manfred Eppe, Stefan Wermter, Sven Magg","submitted_at":"2018-09-17T12:01:02Z","abstract_excerpt":"Deep reinforcement learning has recently gained a focus on problems where policy or value functions are independent of goals. Evidence exists that the sampling of goals has a strong effect on the learning performance, but there is a lack of general mechanisms that focus on optimizing the goal sampling process. In this work, we present a simple and general goal masking method that also allows us to estimate a goal's difficulty level and thus realize a curriculum learning approach for deep RL. Our results indicate that focusing on goals with a medium difficulty level is appropriate for deep dete"},"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":"1809.06146","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-17T12:01:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"988dbc4d78083a043ba0d563ab23a0dffa30fe4e919a0a440ea3c15a75ccd580","abstract_canon_sha256":"9413552fc0ac89f0ebb1256e8156d77cce96ec7d049f57fbc74f9306aec2a838"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:07.117006Z","signature_b64":"EbXW4lpkmzoIqxGL9kb2MRU2JSeuvtWNbVuE65BXmisGLIVoaOz8MfS0osvVQ+UtN26q63B77j4uvq4RZW4eCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bad5e6817572d5f8f3ef0f1b7f55bc59043453f88f35a40f053bd4cc05a1e75c","last_reissued_at":"2026-05-17T23:54:07.116577Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:07.116577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curriculum goal masking for continuous deep reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Manfred Eppe, Stefan Wermter, Sven Magg","submitted_at":"2018-09-17T12:01:02Z","abstract_excerpt":"Deep reinforcement learning has recently gained a focus on problems where policy or value functions are independent of goals. Evidence exists that the sampling of goals has a strong effect on the learning performance, but there is a lack of general mechanisms that focus on optimizing the goal sampling process. In this work, we present a simple and general goal masking method that also allows us to estimate a goal's difficulty level and thus realize a curriculum learning approach for deep RL. Our results indicate that focusing on goals with a medium difficulty level is appropriate for deep dete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06146","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":"1809.06146","created_at":"2026-05-17T23:54:07.116644+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.06146v2","created_at":"2026-05-17T23:54:07.116644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06146","created_at":"2026-05-17T23:54:07.116644+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLK6NALVOLK7","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLK6NALVOLK7R47P","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLK6NALV","created_at":"2026-05-18T12:33:01.666342+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/XLK6NALVOLK7R47PB4NX6VN4LE","json":"https://pith.science/pith/XLK6NALVOLK7R47PB4NX6VN4LE.json","graph_json":"https://pith.science/api/pith-number/XLK6NALVOLK7R47PB4NX6VN4LE/graph.json","events_json":"https://pith.science/api/pith-number/XLK6NALVOLK7R47PB4NX6VN4LE/events.json","paper":"https://pith.science/paper/XLK6NALV"},"agent_actions":{"view_html":"https://pith.science/pith/XLK6NALVOLK7R47PB4NX6VN4LE","download_json":"https://pith.science/pith/XLK6NALVOLK7R47PB4NX6VN4LE.json","view_paper":"https://pith.science/paper/XLK6NALV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.06146&json=true","fetch_graph":"https://pith.science/api/pith-number/XLK6NALVOLK7R47PB4NX6VN4LE/graph.json","fetch_events":"https://pith.science/api/pith-number/XLK6NALVOLK7R47PB4NX6VN4LE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLK6NALVOLK7R47PB4NX6VN4LE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLK6NALVOLK7R47PB4NX6VN4LE/action/storage_attestation","attest_author":"https://pith.science/pith/XLK6NALVOLK7R47PB4NX6VN4LE/action/author_attestation","sign_citation":"https://pith.science/pith/XLK6NALVOLK7R47PB4NX6VN4LE/action/citation_signature","submit_replication":"https://pith.science/pith/XLK6NALVOLK7R47PB4NX6VN4LE/action/replication_record"}},"created_at":"2026-05-17T23:54:07.116644+00:00","updated_at":"2026-05-17T23:54:07.116644+00:00"}