{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HCPGADKWOAYTGKHVXKM4BAAPPO","short_pith_number":"pith:HCPGADKW","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"},"canonical_sha256":"389e600d5670313328f5ba99c0800f7b81176948bd1a0efd5406917cbd80c983","source":{"kind":"arxiv","id":"1810.11748","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11748","created_at":"2026-05-18T00:02:07Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11748v1","created_at":"2026-05-18T00:02:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11748","created_at":"2026-05-18T00:02:07Z"},{"alias_kind":"pith_short_12","alias_value":"HCPGADKWOAYT","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HCPGADKWOAYTGKHV","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HCPGADKW","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HCPGADKWOAYTGKHVXKM4BAAPPO","target":"record","payload":{"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"},"canonical_sha256":"389e600d5670313328f5ba99c0800f7b81176948bd1a0efd5406917cbd80c983","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"},"source_kind":"arxiv","source_id":"1810.11748","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BWmJszPy4UKc7B04seVqG+VmfVXR5EMO1dZg5uAH3EV1Wn7kEzMW9rapSRlXqjUFmBo3TVoYot4CMUUXRJT0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T22:21:19.633371Z"},"content_sha256":"029c357c51dd57904505efa51a0ab869dbb209f83595648afcad93a10159857d","schema_version":"1.0","event_id":"sha256:029c357c51dd57904505efa51a0ab869dbb209f83595648afcad93a10159857d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HCPGADKWOAYTGKHVXKM4BAAPPO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"grp4ncrqtI6umHzV/XSWl3+Pc2JcEVJ8ElYLLM59jzGWiTv8Fc9eee7MnQrkW0RqddRHemnvANi+zTslgx37DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T22:21:19.633744Z"},"content_sha256":"d7ab885aafbc1627c39714f30c2461f62632e3d5cf4f2560930c862cccc1bc57","schema_version":"1.0","event_id":"sha256:d7ab885aafbc1627c39714f30c2461f62632e3d5cf4f2560930c862cccc1bc57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO/bundle.json","state_url":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HCPGADKWOAYTGKHVXKM4BAAPPO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-19T22:21:19Z","links":{"resolver":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO","bundle":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO/bundle.json","state":"https://pith.science/pith/HCPGADKWOAYTGKHVXKM4BAAPPO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HCPGADKWOAYTGKHVXKM4BAAPPO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HCPGADKWOAYTGKHVXKM4BAAPPO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"46dadfe324abe61335d07c298df69d0a58a066ce84592c355fbd6d78c7f24abc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2018-10-28T02:18:40Z","title_canon_sha256":"70ff3c0e29142df8818d315816db4ed082563a092be4c15d1ca4f3fe4f4c0428"},"schema_version":"1.0","source":{"id":"1810.11748","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11748","created_at":"2026-05-18T00:02:07Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11748v1","created_at":"2026-05-18T00:02:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11748","created_at":"2026-05-18T00:02:07Z"},{"alias_kind":"pith_short_12","alias_value":"HCPGADKWOAYT","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HCPGADKWOAYTGKHV","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HCPGADKW","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:d7ab885aafbc1627c39714f30c2461f62632e3d5cf4f2560930c862cccc1bc57","target":"graph","created_at":"2026-05-18T00:02:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Riku Arakawa, Shin-ichi Maeda, Sosuke Kobayashi, Yuta Tsuboi, Yuya Unno","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2018-10-28T02:18:40Z","title":"DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11748","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:029c357c51dd57904505efa51a0ab869dbb209f83595648afcad93a10159857d","target":"record","created_at":"2026-05-18T00:02:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"46dadfe324abe61335d07c298df69d0a58a066ce84592c355fbd6d78c7f24abc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2018-10-28T02:18:40Z","title_canon_sha256":"70ff3c0e29142df8818d315816db4ed082563a092be4c15d1ca4f3fe4f4c0428"},"schema_version":"1.0","source":{"id":"1810.11748","kind":"arxiv","version":1}},"canonical_sha256":"389e600d5670313328f5ba99c0800f7b81176948bd1a0efd5406917cbd80c983","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"389e600d5670313328f5ba99c0800f7b81176948bd1a0efd5406917cbd80c983","first_computed_at":"2026-05-18T00:02:07.538636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:07.538636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kKMcCQqrWsd+Fy3TTmDR5wbdbcDR1BUtAp2ahTlAsiffZ7HdZBvpm2lew6XG+XmE5X2g95AxBc8OPeRvsBEVCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:07.539362Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.11748","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:029c357c51dd57904505efa51a0ab869dbb209f83595648afcad93a10159857d","sha256:d7ab885aafbc1627c39714f30c2461f62632e3d5cf4f2560930c862cccc1bc57"],"state_sha256":"b6dd06edee51b8e3fa3baae3c9905b6f86b33ec632582f3b65aefe92b94e1bce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4MReY94lJutLwJpNFTIc5PqQclYOMvlKlTr4FG9MeWuGQkc+LDGYizL47QpMWZDhDFz06TYW7aGjsNOHNL3dAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T22:21:19.635723Z","bundle_sha256":"e58cd409e0e29a7da5e18ab9910e7c15894ae95d5a8e49957cc7ef9c7bbdcdff"}}