{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KUX44WDZAFASJ5AGIIVCVMBBAR","short_pith_number":"pith:KUX44WDZ","schema_version":"1.0","canonical_sha256":"552fce5879014124f406422a2ab0210465ba64685007cc1b3241c5833171e66c","source":{"kind":"arxiv","id":"1802.06070","version":6},"attestation_state":"computed","paper":{"title":"Diversity is All You Need: Learning Skills without a Reward Function","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Abhishek Gupta, Benjamin Eysenbach, Julian Ibarz, Sergey Levine","submitted_at":"2018-02-16T18:57:57Z","abstract_excerpt":"Intelligent creatures can explore their environments and learn useful skills without supervision. In this paper, we propose DIAYN ('Diversity is All You Need'), a method for learning useful skills without a reward function. Our proposed method learns skills by maximizing an information theoretic objective using a maximum entropy policy. On a variety of simulated robotic tasks, we show that this simple objective results in the unsupervised emergence of diverse skills, such as walking and jumping. In a number of reinforcement learning benchmark environments, our method is able to learn a skill t"},"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":"1802.06070","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-16T18:57:57Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"fac9e0ce19d8a4a615da11369557bce69c35f833332ae6d547214377ace5b5d1","abstract_canon_sha256":"6377a3648606531ce1a44da42e48a545f61f6a05be85a2eff38f9a8a65b06042"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:41.527837Z","signature_b64":"yZKONkY89aoImAXcu4fuUHwKf9z3C4P1QUBXe5MqXDa4Ek+ZgEjir4bdRetnxzy9kahIHGQuBmx4NOqT7kIwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"552fce5879014124f406422a2ab0210465ba64685007cc1b3241c5833171e66c","last_reissued_at":"2026-05-18T00:03:41.527452Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:41.527452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diversity is All You Need: Learning Skills without a Reward Function","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Abhishek Gupta, Benjamin Eysenbach, Julian Ibarz, Sergey Levine","submitted_at":"2018-02-16T18:57:57Z","abstract_excerpt":"Intelligent creatures can explore their environments and learn useful skills without supervision. In this paper, we propose DIAYN ('Diversity is All You Need'), a method for learning useful skills without a reward function. Our proposed method learns skills by maximizing an information theoretic objective using a maximum entropy policy. On a variety of simulated robotic tasks, we show that this simple objective results in the unsupervised emergence of diverse skills, such as walking and jumping. In a number of reinforcement learning benchmark environments, our method is able to learn a skill t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06070","kind":"arxiv","version":6},"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":"1802.06070","created_at":"2026-05-18T00:03:41.527508+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.06070v6","created_at":"2026-05-18T00:03:41.527508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06070","created_at":"2026-05-18T00:03:41.527508+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUX44WDZAFAS","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUX44WDZAFASJ5AG","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUX44WDZ","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16725","citing_title":"Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12261","citing_title":"Delay-Empowered Causal Hierarchical Reinforcement Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24558","citing_title":"Hierarchical Behaviour Spaces","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01242","citing_title":"Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15414","citing_title":"Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20381","citing_title":"Distributional Value Estimation Without Target Networks for Robust Quality-Diversity","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KUX44WDZAFASJ5AGIIVCVMBBAR","json":"https://pith.science/pith/KUX44WDZAFASJ5AGIIVCVMBBAR.json","graph_json":"https://pith.science/api/pith-number/KUX44WDZAFASJ5AGIIVCVMBBAR/graph.json","events_json":"https://pith.science/api/pith-number/KUX44WDZAFASJ5AGIIVCVMBBAR/events.json","paper":"https://pith.science/paper/KUX44WDZ"},"agent_actions":{"view_html":"https://pith.science/pith/KUX44WDZAFASJ5AGIIVCVMBBAR","download_json":"https://pith.science/pith/KUX44WDZAFASJ5AGIIVCVMBBAR.json","view_paper":"https://pith.science/paper/KUX44WDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.06070&json=true","fetch_graph":"https://pith.science/api/pith-number/KUX44WDZAFASJ5AGIIVCVMBBAR/graph.json","fetch_events":"https://pith.science/api/pith-number/KUX44WDZAFASJ5AGIIVCVMBBAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUX44WDZAFASJ5AGIIVCVMBBAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUX44WDZAFASJ5AGIIVCVMBBAR/action/storage_attestation","attest_author":"https://pith.science/pith/KUX44WDZAFASJ5AGIIVCVMBBAR/action/author_attestation","sign_citation":"https://pith.science/pith/KUX44WDZAFASJ5AGIIVCVMBBAR/action/citation_signature","submit_replication":"https://pith.science/pith/KUX44WDZAFASJ5AGIIVCVMBBAR/action/replication_record"}},"created_at":"2026-05-18T00:03:41.527508+00:00","updated_at":"2026-05-18T00:03:41.527508+00:00"}