{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GXIRMJ6UERXKJTI42UPLHRGKNF","short_pith_number":"pith:GXIRMJ6U","schema_version":"1.0","canonical_sha256":"35d11627d4246ea4cd1cd51eb3c4ca69543ae6842859a9fe3d3a9b258d247b13","source":{"kind":"arxiv","id":"1901.08486","version":1},"attestation_state":"computed","paper":{"title":"Never Forget: Balancing Exploration and Exploitation via Learning Optical Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Chun-Yi Lee, Hsuan-Kung Yang, Kuan-Wei Ho, Min-Fong Hong, Po-Han Chiang","submitted_at":"2019-01-24T16:26:16Z","abstract_excerpt":"Exploration bonus derived from the novelty of the states in an environment has become a popular approach to motivate exploration for deep reinforcement learning agents in the past few years. Recent methods such as curiosity-driven exploration usually estimate the novelty of new observations by the prediction errors of their system dynamics models. Due to the capacity limitation of the models and difficulty of performing next-frame prediction, however, these methods typically fail to balance between exploration and exploitation in high-dimensional observation tasks, resulting in the agents forg"},"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":"1901.08486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T16:26:16Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"33a3198c5aaef2aa796590631e33cf4b33b9ab2be141d813ef8f0298923f3f44","abstract_canon_sha256":"a9234216d8fadf71c219a85b8c7b3099db26681c8339c299292d7c1316cf8182"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:35.345012Z","signature_b64":"HBf/cuD6+WUMVdBrcG12eLkPGlxrPruKZ2JcT1eOCseewxBuddHNiDBdmCiihveAqbvG3pvhcgPGejjWtk1dBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35d11627d4246ea4cd1cd51eb3c4ca69543ae6842859a9fe3d3a9b258d247b13","last_reissued_at":"2026-05-17T23:55:35.344411Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:35.344411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Never Forget: Balancing Exploration and Exploitation via Learning Optical Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Chun-Yi Lee, Hsuan-Kung Yang, Kuan-Wei Ho, Min-Fong Hong, Po-Han Chiang","submitted_at":"2019-01-24T16:26:16Z","abstract_excerpt":"Exploration bonus derived from the novelty of the states in an environment has become a popular approach to motivate exploration for deep reinforcement learning agents in the past few years. Recent methods such as curiosity-driven exploration usually estimate the novelty of new observations by the prediction errors of their system dynamics models. Due to the capacity limitation of the models and difficulty of performing next-frame prediction, however, these methods typically fail to balance between exploration and exploitation in high-dimensional observation tasks, resulting in the agents forg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08486","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":"1901.08486","created_at":"2026-05-17T23:55:35.344494+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08486v1","created_at":"2026-05-17T23:55:35.344494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08486","created_at":"2026-05-17T23:55:35.344494+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXIRMJ6UERXK","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXIRMJ6UERXKJTI4","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXIRMJ6U","created_at":"2026-05-18T12:33:18.533446+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/GXIRMJ6UERXKJTI42UPLHRGKNF","json":"https://pith.science/pith/GXIRMJ6UERXKJTI42UPLHRGKNF.json","graph_json":"https://pith.science/api/pith-number/GXIRMJ6UERXKJTI42UPLHRGKNF/graph.json","events_json":"https://pith.science/api/pith-number/GXIRMJ6UERXKJTI42UPLHRGKNF/events.json","paper":"https://pith.science/paper/GXIRMJ6U"},"agent_actions":{"view_html":"https://pith.science/pith/GXIRMJ6UERXKJTI42UPLHRGKNF","download_json":"https://pith.science/pith/GXIRMJ6UERXKJTI42UPLHRGKNF.json","view_paper":"https://pith.science/paper/GXIRMJ6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08486&json=true","fetch_graph":"https://pith.science/api/pith-number/GXIRMJ6UERXKJTI42UPLHRGKNF/graph.json","fetch_events":"https://pith.science/api/pith-number/GXIRMJ6UERXKJTI42UPLHRGKNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXIRMJ6UERXKJTI42UPLHRGKNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXIRMJ6UERXKJTI42UPLHRGKNF/action/storage_attestation","attest_author":"https://pith.science/pith/GXIRMJ6UERXKJTI42UPLHRGKNF/action/author_attestation","sign_citation":"https://pith.science/pith/GXIRMJ6UERXKJTI42UPLHRGKNF/action/citation_signature","submit_replication":"https://pith.science/pith/GXIRMJ6UERXKJTI42UPLHRGKNF/action/replication_record"}},"created_at":"2026-05-17T23:55:35.344494+00:00","updated_at":"2026-05-17T23:55:35.344494+00:00"}