{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:4KAI5ADKR7RBPM4PFRRCEDEB3W","short_pith_number":"pith:4KAI5ADK","schema_version":"1.0","canonical_sha256":"e2808e806a8fe217b38f2c62220c81dd85a00a44fa9b96bae8870c11ca961def","source":{"kind":"arxiv","id":"1611.05397","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"David Silver, Joel Z Leibo, Koray Kavukcuoglu, Max Jaderberg, Tom Schaul, Volodymyr Mnih, Wojciech Marian Czarnecki","submitted_at":"2016-11-16T18:21:29Z","abstract_excerpt":"Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible training signals. In this paper, we introduce an agent that also maximises many other pseudo-reward functions simultaneously by reinforcement learning. All of these tasks share a common representation that, like unsupervised learning, continues to develop in the absence of extrinsic rewards. We also introduce a novel mechanism for focusing this representation upon extrinsic rewards, so that learning can rapidly adapt "},"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":"1611.05397","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-16T18:21:29Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"87229cfef734bbdf23312fb0c8f8fd7b60bb64ae89b3435d0b42cde749fea964","abstract_canon_sha256":"01b0ca783d40f6e65b291f689034fc545882796f3f289e089142fdd63022f020"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:27.200647Z","signature_b64":"468xtJd05wUxqYkosWgXw5symZSuJFY9eESAIqgCWs702HmcBbMqIKRAmSs/AGi4PVr1gHEl2pEeucFIJdwAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2808e806a8fe217b38f2c62220c81dd85a00a44fa9b96bae8870c11ca961def","last_reissued_at":"2026-05-18T00:58:27.200013Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:27.200013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"David Silver, Joel Z Leibo, Koray Kavukcuoglu, Max Jaderberg, Tom Schaul, Volodymyr Mnih, Wojciech Marian Czarnecki","submitted_at":"2016-11-16T18:21:29Z","abstract_excerpt":"Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible training signals. In this paper, we introduce an agent that also maximises many other pseudo-reward functions simultaneously by reinforcement learning. All of these tasks share a common representation that, like unsupervised learning, continues to develop in the absence of extrinsic rewards. We also introduce a novel mechanism for focusing this representation upon extrinsic rewards, so that learning can rapidly adapt "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05397","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":"1611.05397","created_at":"2026-05-18T00:58:27.200106+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.05397v1","created_at":"2026-05-18T00:58:27.200106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05397","created_at":"2026-05-18T00:58:27.200106+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KAI5ADKR7RB","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KAI5ADKR7RBPM4P","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KAI5ADK","created_at":"2026-05-18T12:29:58.707656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"1906.09205","citing_title":"Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"1906.09237","citing_title":"Shaping Belief States with Generative Environment Models for RL","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"1906.09510","citing_title":"Learning Belief Representations for Imitation Learning in POMDPs","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11951","citing_title":"Supervise Thyself: Examining Self-Supervised Representations in Interactive Environments","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23551","citing_title":"Goal-Conditioned Agents that Learn Everything All at Once","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11770","citing_title":"To Learn or Not to Learn: Analyzing the Role of Learning for Navigation in Virtual Environments","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"1911.08265","citing_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02391","citing_title":"Reliability-Aware Geometric Fusion for Robust Audio-Visual Navigation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03189","citing_title":"Reflective Context Learning: Studying the Optimization Primitives of Context Space","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"1912.01603","citing_title":"Dream to Control: Learning Behaviors by Latent Imagination","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24532","citing_title":"A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2301.04104","citing_title":"Mastering Diverse Domains through World Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W","json":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W.json","graph_json":"https://pith.science/api/pith-number/4KAI5ADKR7RBPM4PFRRCEDEB3W/graph.json","events_json":"https://pith.science/api/pith-number/4KAI5ADKR7RBPM4PFRRCEDEB3W/events.json","paper":"https://pith.science/paper/4KAI5ADK"},"agent_actions":{"view_html":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W","download_json":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W.json","view_paper":"https://pith.science/paper/4KAI5ADK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.05397&json=true","fetch_graph":"https://pith.science/api/pith-number/4KAI5ADKR7RBPM4PFRRCEDEB3W/graph.json","fetch_events":"https://pith.science/api/pith-number/4KAI5ADKR7RBPM4PFRRCEDEB3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W/action/storage_attestation","attest_author":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W/action/author_attestation","sign_citation":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W/action/citation_signature","submit_replication":"https://pith.science/pith/4KAI5ADKR7RBPM4PFRRCEDEB3W/action/replication_record"}},"created_at":"2026-05-18T00:58:27.200106+00:00","updated_at":"2026-05-18T00:58:27.200106+00:00"}