{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:HJN5HFXKNQ42WWFL23GT3R7SVK","short_pith_number":"pith:HJN5HFXK","schema_version":"1.0","canonical_sha256":"3a5bd396ea6c39ab58abd6cd3dc7f2aa9571c6fbd848beaa4a7138a504214eec","source":{"kind":"arxiv","id":"1512.02011","version":2},"attestation_state":"computed","paper":{"title":"How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Damien Ernst, Raphael Fonteneau, Vincent Fran\\c{c}ois-Lavet","submitted_at":"2015-12-07T12:25:18Z","abstract_excerpt":"Using deep neural nets as function approximator for reinforcement learning tasks have recently been shown to be very powerful for solving problems approaching real-world complexity. Using these results as a benchmark, we discuss the role that the discount factor may play in the quality of the learning process of a deep Q-network (DQN). When the discount factor progressively increases up to its final value, we empirically show that it is possible to significantly reduce the number of learning steps. When used in conjunction with a varying learning rate, we empirically show that it outperforms o"},"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":"1512.02011","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-07T12:25:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd16d4e7fcbf9a2a970a6ca80716a739ed8a7b98662310ed1fb0e1b42237b4b5","abstract_canon_sha256":"3bae816b910e51e0b206af38b9919d20ed40289d7d4eacfa086fbf1ae3a5eec1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:22:18.170987Z","signature_b64":"MWElvErrylqFAkxei2KeG6OH2PYpNha9POMNxCKcKkFlXRp6Qkz+LHQvpVlIHv93X0JRxzU3OkuO/yRs94ToBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a5bd396ea6c39ab58abd6cd3dc7f2aa9571c6fbd848beaa4a7138a504214eec","last_reissued_at":"2026-05-18T01:22:18.170571Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:22:18.170571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Damien Ernst, Raphael Fonteneau, Vincent Fran\\c{c}ois-Lavet","submitted_at":"2015-12-07T12:25:18Z","abstract_excerpt":"Using deep neural nets as function approximator for reinforcement learning tasks have recently been shown to be very powerful for solving problems approaching real-world complexity. Using these results as a benchmark, we discuss the role that the discount factor may play in the quality of the learning process of a deep Q-network (DQN). When the discount factor progressively increases up to its final value, we empirically show that it is possible to significantly reduce the number of learning steps. When used in conjunction with a varying learning rate, we empirically show that it outperforms o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.02011","kind":"arxiv","version":2},"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":"1512.02011","created_at":"2026-05-18T01:22:18.170631+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.02011v2","created_at":"2026-05-18T01:22:18.170631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.02011","created_at":"2026-05-18T01:22:18.170631+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJN5HFXKNQ42","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJN5HFXKNQ42WWFL","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJN5HFXK","created_at":"2026-05-18T12:29:25.134429+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/HJN5HFXKNQ42WWFL23GT3R7SVK","json":"https://pith.science/pith/HJN5HFXKNQ42WWFL23GT3R7SVK.json","graph_json":"https://pith.science/api/pith-number/HJN5HFXKNQ42WWFL23GT3R7SVK/graph.json","events_json":"https://pith.science/api/pith-number/HJN5HFXKNQ42WWFL23GT3R7SVK/events.json","paper":"https://pith.science/paper/HJN5HFXK"},"agent_actions":{"view_html":"https://pith.science/pith/HJN5HFXKNQ42WWFL23GT3R7SVK","download_json":"https://pith.science/pith/HJN5HFXKNQ42WWFL23GT3R7SVK.json","view_paper":"https://pith.science/paper/HJN5HFXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.02011&json=true","fetch_graph":"https://pith.science/api/pith-number/HJN5HFXKNQ42WWFL23GT3R7SVK/graph.json","fetch_events":"https://pith.science/api/pith-number/HJN5HFXKNQ42WWFL23GT3R7SVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJN5HFXKNQ42WWFL23GT3R7SVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJN5HFXKNQ42WWFL23GT3R7SVK/action/storage_attestation","attest_author":"https://pith.science/pith/HJN5HFXKNQ42WWFL23GT3R7SVK/action/author_attestation","sign_citation":"https://pith.science/pith/HJN5HFXKNQ42WWFL23GT3R7SVK/action/citation_signature","submit_replication":"https://pith.science/pith/HJN5HFXKNQ42WWFL23GT3R7SVK/action/replication_record"}},"created_at":"2026-05-18T01:22:18.170631+00:00","updated_at":"2026-05-18T01:22:18.170631+00:00"}