{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QQVZ4Z5TFV2HLMIH6WOVT2J3AS","short_pith_number":"pith:QQVZ4Z5T","schema_version":"1.0","canonical_sha256":"842b9e67b32d7475b107f59d59e93b048b9a04b138f3294b88d6ab3acf8bf6d3","source":{"kind":"arxiv","id":"1804.01238","version":1},"attestation_state":"computed","paper":{"title":"Information Maximizing Exploration with a Latent Dynamics Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Heni Ben Amor, Oliver Obst, Trevor Barron","submitted_at":"2018-04-04T05:04:41Z","abstract_excerpt":"All reinforcement learning algorithms must handle the trade-off between exploration and exploitation. Many state-of-the-art deep reinforcement learning methods use noise in the action selection, such as Gaussian noise in policy gradient methods or $\\epsilon$-greedy in Q-learning. While these methods are appealing due to their simplicity, they do not explore the state space in a methodical manner. We present an approach that uses a model to derive reward bonuses as a means of intrinsic motivation to improve model-free reinforcement learning. A key insight of our approach is that this dynamics m"},"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":"1804.01238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-04T05:04:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"798467550a8686512be65141c6606adb29c2fbf547e55a6b68eecf3bff6eeaf3","abstract_canon_sha256":"7ae2c60aa90b88bcebc687ef2675034e1f5805e41b12d394741132d1a1c917a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:15.640203Z","signature_b64":"8Q/L1i4+Z1rukXTzeyZAbiUJOZADyHNLS85QhiU+mfqG2sJs5MfE7VunPia60EV3jWRLgK7WCsAttEG1Cya5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"842b9e67b32d7475b107f59d59e93b048b9a04b138f3294b88d6ab3acf8bf6d3","last_reissued_at":"2026-05-18T00:19:15.639518Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:15.639518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information Maximizing Exploration with a Latent Dynamics Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Heni Ben Amor, Oliver Obst, Trevor Barron","submitted_at":"2018-04-04T05:04:41Z","abstract_excerpt":"All reinforcement learning algorithms must handle the trade-off between exploration and exploitation. Many state-of-the-art deep reinforcement learning methods use noise in the action selection, such as Gaussian noise in policy gradient methods or $\\epsilon$-greedy in Q-learning. While these methods are appealing due to their simplicity, they do not explore the state space in a methodical manner. We present an approach that uses a model to derive reward bonuses as a means of intrinsic motivation to improve model-free reinforcement learning. A key insight of our approach is that this dynamics m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01238","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":"1804.01238","created_at":"2026-05-18T00:19:15.639634+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.01238v1","created_at":"2026-05-18T00:19:15.639634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01238","created_at":"2026-05-18T00:19:15.639634+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQVZ4Z5TFV2H","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQVZ4Z5TFV2HLMIH","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQVZ4Z5T","created_at":"2026-05-18T12:32:46.962924+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/QQVZ4Z5TFV2HLMIH6WOVT2J3AS","json":"https://pith.science/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS.json","graph_json":"https://pith.science/api/pith-number/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/graph.json","events_json":"https://pith.science/api/pith-number/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/events.json","paper":"https://pith.science/paper/QQVZ4Z5T"},"agent_actions":{"view_html":"https://pith.science/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS","download_json":"https://pith.science/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS.json","view_paper":"https://pith.science/paper/QQVZ4Z5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.01238&json=true","fetch_graph":"https://pith.science/api/pith-number/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/graph.json","fetch_events":"https://pith.science/api/pith-number/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/action/storage_attestation","attest_author":"https://pith.science/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/action/author_attestation","sign_citation":"https://pith.science/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/action/citation_signature","submit_replication":"https://pith.science/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/action/replication_record"}},"created_at":"2026-05-18T00:19:15.639634+00:00","updated_at":"2026-05-18T00:19:15.639634+00:00"}