{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VIEYGTD6FCQRIVUNBZF7XI3DLM","short_pith_number":"pith:VIEYGTD6","schema_version":"1.0","canonical_sha256":"aa09834c7e28a114568d0e4bfba3635b3c8338fc8da6a5515172a6063a5553f4","source":{"kind":"arxiv","id":"1802.10567","version":1},"attestation_state":"computed","paper":{"title":"Learning by Playing - Solving Sparse Reward Tasks from Scratch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jonas Degrave, Jost Tobias Springenberg, Martin Riedmiller, Michael Neunert, Nicolas Heess, Roland Hafner, Thomas Lampe, Tom Van de Wiele, Volodymyr Mnih","submitted_at":"2018-02-28T18:15:49Z","abstract_excerpt":"We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors - from scratch - in the presence of multiple sparse reward signals. To this end, the agent is equipped with a set of general auxiliary tasks, that it attempts to learn simultaneously via off-policy RL. The key idea behind our method is that active (learned) scheduling and execution of auxiliary policies allows the agent to efficiently explore its environment - enabling it to excel at sparse reward RL. Our experiments in several chall"},"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":"1802.10567","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-28T18:15:49Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"ac3923e650a052ab34ee764edf7537b99e42b3fd4a614465280ee253a84b1c4d","abstract_canon_sha256":"b635fbf9fc709c7964affe542e688660b7996cb9ad0aba21e5b5af74ebd6722d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:16.768613Z","signature_b64":"+OLPQ9C/hq56wk6vax4PGqNXOTeBhxJEUZPJxvm2BR9CmKQEaSf7pt6C60I5l3ZqHVyPgjYwnEXdMkXaR9sUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa09834c7e28a114568d0e4bfba3635b3c8338fc8da6a5515172a6063a5553f4","last_reissued_at":"2026-05-18T00:22:16.768073Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:16.768073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning by Playing - Solving Sparse Reward Tasks from Scratch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jonas Degrave, Jost Tobias Springenberg, Martin Riedmiller, Michael Neunert, Nicolas Heess, Roland Hafner, Thomas Lampe, Tom Van de Wiele, Volodymyr Mnih","submitted_at":"2018-02-28T18:15:49Z","abstract_excerpt":"We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors - from scratch - in the presence of multiple sparse reward signals. To this end, the agent is equipped with a set of general auxiliary tasks, that it attempts to learn simultaneously via off-policy RL. The key idea behind our method is that active (learned) scheduling and execution of auxiliary policies allows the agent to efficiently explore its environment - enabling it to excel at sparse reward RL. Our experiments in several chall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10567","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":"1802.10567","created_at":"2026-05-18T00:22:16.768160+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.10567v1","created_at":"2026-05-18T00:22:16.768160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10567","created_at":"2026-05-18T00:22:16.768160+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIEYGTD6FCQR","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIEYGTD6FCQRIVUN","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIEYGTD6","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07505","citing_title":"Reinforcement Learning via Implicit Imitation Guidance","ref_index":2017,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VIEYGTD6FCQRIVUNBZF7XI3DLM","json":"https://pith.science/pith/VIEYGTD6FCQRIVUNBZF7XI3DLM.json","graph_json":"https://pith.science/api/pith-number/VIEYGTD6FCQRIVUNBZF7XI3DLM/graph.json","events_json":"https://pith.science/api/pith-number/VIEYGTD6FCQRIVUNBZF7XI3DLM/events.json","paper":"https://pith.science/paper/VIEYGTD6"},"agent_actions":{"view_html":"https://pith.science/pith/VIEYGTD6FCQRIVUNBZF7XI3DLM","download_json":"https://pith.science/pith/VIEYGTD6FCQRIVUNBZF7XI3DLM.json","view_paper":"https://pith.science/paper/VIEYGTD6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.10567&json=true","fetch_graph":"https://pith.science/api/pith-number/VIEYGTD6FCQRIVUNBZF7XI3DLM/graph.json","fetch_events":"https://pith.science/api/pith-number/VIEYGTD6FCQRIVUNBZF7XI3DLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIEYGTD6FCQRIVUNBZF7XI3DLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIEYGTD6FCQRIVUNBZF7XI3DLM/action/storage_attestation","attest_author":"https://pith.science/pith/VIEYGTD6FCQRIVUNBZF7XI3DLM/action/author_attestation","sign_citation":"https://pith.science/pith/VIEYGTD6FCQRIVUNBZF7XI3DLM/action/citation_signature","submit_replication":"https://pith.science/pith/VIEYGTD6FCQRIVUNBZF7XI3DLM/action/replication_record"}},"created_at":"2026-05-18T00:22:16.768160+00:00","updated_at":"2026-05-18T00:22:16.768160+00:00"}