{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HCPGADKWOAYTGKHVXKM4BAAPPO","short_pith_number":"pith:HCPGADKW","schema_version":"1.0","canonical_sha256":"389e600d5670313328f5ba99c0800f7b81176948bd1a0efd5406917cbd80c983","source":{"kind":"arxiv","id":"1810.11748","version":1},"attestation_state":"computed","paper":{"title":"DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.HC","authors_text":"Riku Arakawa, Shin-ichi Maeda, Sosuke Kobayashi, Yuta Tsuboi, Yuya Unno","submitted_at":"2018-10-28T02:18:40Z","abstract_excerpt":"Exploration has been one of the greatest challenges in reinforcement learning (RL), which is a large obstacle in the application of RL to robotics. Even with state-of-the-art RL algorithms, building a well-learned agent often requires too many trials, mainly due to the difficulty of matching its actions with rewards in the distant future. A remedy for this is to train an agent with real-time feedback from a human observer who immediately gives rewards for some actions. This study tackles a series of challenges for introducing such a human-in-the-loop RL scheme. The first contribution of this w"},"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":"1810.11748","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2018-10-28T02:18:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"70ff3c0e29142df8818d315816db4ed082563a092be4c15d1ca4f3fe4f4c0428","abstract_canon_sha256":"46dadfe324abe61335d07c298df69d0a58a066ce84592c355fbd6d78c7f24abc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:07.539362Z","signature_b64":"kKMcCQqrWsd+Fy3TTmDR5wbdbcDR1BUtAp2ahTlAsiffZ7HdZBvpm2lew6XG+XmE5X2g95AxBc8OPeRvsBEVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"389e600d5670313328f5ba99c0800f7b81176948bd1a0efd5406917cbd80c983","last_reissued_at":"2026-05-18T00:02:07.538636Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:07.538636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.HC","authors_text":"Riku Arakawa, Shin-ichi Maeda, Sosuke Kobayashi, Yuta Tsuboi, Yuya Unno","submitted_at":"2018-10-28T02:18:40Z","abstract_excerpt":"Exploration has been one of the greatest challenges in reinforcement learning (RL), which is a large obstacle in the application of RL to robotics. Even with state-of-the-art RL algorithms, building a well-learned agent often requires too many trials, mainly due to the difficulty of matching its actions with rewards in the distant future. A remedy for this is to train an agent with real-time feedback from a human observer who immediately gives rewards for some actions. This study tackles a series of challenges for introducing such a human-in-the-loop RL scheme. The first contribution of this w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11748","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":"1810.11748","created_at":"2026-05-18T00:02:07.538762+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.11748v1","created_at":"2026-05-18T00:02:07.538762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11748","created_at":"2026-05-18T00:02:07.538762+00:00"},{"alias_kind":"pith_short_12","alias_value":"HCPGADKWOAYT","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HCPGADKWOAYTGKHV","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HCPGADKW","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09128","citing_title":"A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO","json":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO.json","graph_json":"https://pith.science/api/pith-number/HCPGADKWOAYTGKHVXKM4BAAPPO/graph.json","events_json":"https://pith.science/api/pith-number/HCPGADKWOAYTGKHVXKM4BAAPPO/events.json","paper":"https://pith.science/paper/HCPGADKW"},"agent_actions":{"view_html":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO","download_json":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO.json","view_paper":"https://pith.science/paper/HCPGADKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.11748&json=true","fetch_graph":"https://pith.science/api/pith-number/HCPGADKWOAYTGKHVXKM4BAAPPO/graph.json","fetch_events":"https://pith.science/api/pith-number/HCPGADKWOAYTGKHVXKM4BAAPPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO/action/storage_attestation","attest_author":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO/action/author_attestation","sign_citation":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO/action/citation_signature","submit_replication":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO/action/replication_record"}},"created_at":"2026-05-18T00:02:07.538762+00:00","updated_at":"2026-05-18T00:02:07.538762+00:00"}