{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HSU745TQ7RWMSJTEFHPXRVWHLZ","short_pith_number":"pith:HSU745TQ","schema_version":"1.0","canonical_sha256":"3ca9fe7670fc6cc9266429df78d6c75e503bbad12c3a9e3daf1f884471ac0674","source":{"kind":"arxiv","id":"1808.04355","version":1},"attestation_state":"computed","paper":{"title":"Large-Scale Study of Curiosity-Driven Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexei A. Efros, Amos Storkey, Deepak Pathak, Harri Edwards, Trevor Darrell, Yuri Burda","submitted_at":"2018-08-13T17:58:01Z","abstract_excerpt":"Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. Curiosity is a type of intrinsic reward function which uses prediction error as reward signal. In this paper: (a) We perform the first large-scale study of purely curiosity-driven learning, i.e. without any extrinsic rewards, across 54 standard benchmark environments, including the Atari game suite. Our resul"},"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":"1808.04355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-13T17:58:01Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO","stat.ML"],"title_canon_sha256":"b2951204314b8d7cc6d25d4a882daed9d19443c66d74dc5805ba8cae38c1ade4","abstract_canon_sha256":"a9ada91f2d32c26cdf3cef39c5e8460d5b7e53273462cef7a6aee03d05dc5004"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:16.588080Z","signature_b64":"0WqOe2Dzz+v1qsKZFUWXscIkcWFkKlTDCDWq0DJ/pW+GlTx2fi2B4ulFg9pKIDGXBDcmrrAxXfCw7Yg2oquuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ca9fe7670fc6cc9266429df78d6c75e503bbad12c3a9e3daf1f884471ac0674","last_reissued_at":"2026-05-18T00:08:16.587650Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:16.587650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Study of Curiosity-Driven Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexei A. Efros, Amos Storkey, Deepak Pathak, Harri Edwards, Trevor Darrell, Yuri Burda","submitted_at":"2018-08-13T17:58:01Z","abstract_excerpt":"Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. Curiosity is a type of intrinsic reward function which uses prediction error as reward signal. In this paper: (a) We perform the first large-scale study of purely curiosity-driven learning, i.e. without any extrinsic rewards, across 54 standard benchmark environments, including the Atari game suite. Our resul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04355","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":"1808.04355","created_at":"2026-05-18T00:08:16.587713+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.04355v1","created_at":"2026-05-18T00:08:16.587713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04355","created_at":"2026-05-18T00:08:16.587713+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSU745TQ7RWM","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSU745TQ7RWMSJTE","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSU745TQ","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1906.11951","citing_title":"Supervise Thyself: Examining Self-Supervised Representations in Interactive Environments","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00664","citing_title":"Learning World Graphs to Accelerate Hierarchical Reinforcement Learning","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01285","citing_title":"Learning the Arrow of Time","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2509.25438","citing_title":"Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress Monitoring","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2603.03295","citing_title":"Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11688","citing_title":"Shaping Zero-Shot Coordination via State Blocking","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18701","citing_title":"Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ","json":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ.json","graph_json":"https://pith.science/api/pith-number/HSU745TQ7RWMSJTEFHPXRVWHLZ/graph.json","events_json":"https://pith.science/api/pith-number/HSU745TQ7RWMSJTEFHPXRVWHLZ/events.json","paper":"https://pith.science/paper/HSU745TQ"},"agent_actions":{"view_html":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ","download_json":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ.json","view_paper":"https://pith.science/paper/HSU745TQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.04355&json=true","fetch_graph":"https://pith.science/api/pith-number/HSU745TQ7RWMSJTEFHPXRVWHLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/HSU745TQ7RWMSJTEFHPXRVWHLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ/action/storage_attestation","attest_author":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ/action/author_attestation","sign_citation":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ/action/citation_signature","submit_replication":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ/action/replication_record"}},"created_at":"2026-05-18T00:08:16.587713+00:00","updated_at":"2026-05-18T00:08:16.587713+00:00"}