{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:T6UMGKV3LIED2JMDIO7Z72VBUS","short_pith_number":"pith:T6UMGKV3","schema_version":"1.0","canonical_sha256":"9fa8c32abb5a083d258343bf9feaa1a48be74bf68dc297309c93d166758f5ac1","source":{"kind":"arxiv","id":"1812.07452","version":1},"attestation_state":"computed","paper":{"title":"Domain Adaptation for Reinforcement Learning on the Atari","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"George Vogiatzis, Maria Chli, Thomas Carr","submitted_at":"2018-12-18T16:08:57Z","abstract_excerpt":"Deep reinforcement learning agents have recently been successful across a variety of discrete and continuous control tasks; however, they can be slow to train and require a large number of interactions with the environment to learn a suitable policy. This is borne out by the fact that a reinforcement learning agent has no prior knowledge of the world, no pre-existing data to depend on and so must devote considerable time to exploration. Transfer learning can alleviate some of the problems by leveraging learning done on some source task to help learning on some target task. Our work presents an"},"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":"1812.07452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T16:08:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ec9de4919603795d7377c85fae807b4cbc965f267b5a97fad4a4679ed7556401","abstract_canon_sha256":"01345bc2028335bcc0ccd78988f610cc299e209ac4f0b806572c5c3ec40850eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:00.468391Z","signature_b64":"6qcg2NRmRjLEyXwwYQTzKwFnyrJZHavqvJJbbruabKef4U6jzh1eXIKuojlAkx0TXLt4Qw+eVkmS9kwgzI7wDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fa8c32abb5a083d258343bf9feaa1a48be74bf68dc297309c93d166758f5ac1","last_reissued_at":"2026-05-17T23:58:00.467784Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:00.467784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Adaptation for Reinforcement Learning on the Atari","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"George Vogiatzis, Maria Chli, Thomas Carr","submitted_at":"2018-12-18T16:08:57Z","abstract_excerpt":"Deep reinforcement learning agents have recently been successful across a variety of discrete and continuous control tasks; however, they can be slow to train and require a large number of interactions with the environment to learn a suitable policy. This is borne out by the fact that a reinforcement learning agent has no prior knowledge of the world, no pre-existing data to depend on and so must devote considerable time to exploration. Transfer learning can alleviate some of the problems by leveraging learning done on some source task to help learning on some target task. Our work presents an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07452","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":"1812.07452","created_at":"2026-05-17T23:58:00.467875+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.07452v1","created_at":"2026-05-17T23:58:00.467875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07452","created_at":"2026-05-17T23:58:00.467875+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6UMGKV3LIED","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6UMGKV3LIED2JMD","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6UMGKV3","created_at":"2026-05-18T12:32:53.628368+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/T6UMGKV3LIED2JMDIO7Z72VBUS","json":"https://pith.science/pith/T6UMGKV3LIED2JMDIO7Z72VBUS.json","graph_json":"https://pith.science/api/pith-number/T6UMGKV3LIED2JMDIO7Z72VBUS/graph.json","events_json":"https://pith.science/api/pith-number/T6UMGKV3LIED2JMDIO7Z72VBUS/events.json","paper":"https://pith.science/paper/T6UMGKV3"},"agent_actions":{"view_html":"https://pith.science/pith/T6UMGKV3LIED2JMDIO7Z72VBUS","download_json":"https://pith.science/pith/T6UMGKV3LIED2JMDIO7Z72VBUS.json","view_paper":"https://pith.science/paper/T6UMGKV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.07452&json=true","fetch_graph":"https://pith.science/api/pith-number/T6UMGKV3LIED2JMDIO7Z72VBUS/graph.json","fetch_events":"https://pith.science/api/pith-number/T6UMGKV3LIED2JMDIO7Z72VBUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6UMGKV3LIED2JMDIO7Z72VBUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6UMGKV3LIED2JMDIO7Z72VBUS/action/storage_attestation","attest_author":"https://pith.science/pith/T6UMGKV3LIED2JMDIO7Z72VBUS/action/author_attestation","sign_citation":"https://pith.science/pith/T6UMGKV3LIED2JMDIO7Z72VBUS/action/citation_signature","submit_replication":"https://pith.science/pith/T6UMGKV3LIED2JMDIO7Z72VBUS/action/replication_record"}},"created_at":"2026-05-17T23:58:00.467875+00:00","updated_at":"2026-05-17T23:58:00.467875+00:00"}