{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:J7ZJW5SGHDLMCXF22RY2E2C7EI","short_pith_number":"pith:J7ZJW5SG","canonical_record":{"source":{"id":"1905.03501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-09T09:23:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f198e5487868ff86973eb251bf6c8bfcdd0a968e3b389582503a2553d07680e8","abstract_canon_sha256":"9c547e17c480f63f0eec97cf64577c22844a720057aaad1514fbc46bad6d5769"},"schema_version":"1.0"},"canonical_sha256":"4ff29b764638d6c15cbad471a2685f222c0de3fa97ecbbfa95bf3777378f9562","source":{"kind":"arxiv","id":"1905.03501","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.03501","created_at":"2026-05-17T23:46:37Z"},{"alias_kind":"arxiv_version","alias_value":"1905.03501v1","created_at":"2026-05-17T23:46:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03501","created_at":"2026-05-17T23:46:37Z"},{"alias_kind":"pith_short_12","alias_value":"J7ZJW5SGHDLM","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"J7ZJW5SGHDLMCXF2","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"J7ZJW5SG","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:J7ZJW5SGHDLMCXF22RY2E2C7EI","target":"record","payload":{"canonical_record":{"source":{"id":"1905.03501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-09T09:23:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f198e5487868ff86973eb251bf6c8bfcdd0a968e3b389582503a2553d07680e8","abstract_canon_sha256":"9c547e17c480f63f0eec97cf64577c22844a720057aaad1514fbc46bad6d5769"},"schema_version":"1.0"},"canonical_sha256":"4ff29b764638d6c15cbad471a2685f222c0de3fa97ecbbfa95bf3777378f9562","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:37.596912Z","signature_b64":"rWxMDhz0ZGVG3neaIIjjyegKrXZh0jbeEBFnDmwdA2dpD45nOwa8o9WYtzUoxls+5Xy+7xwFbNSTCDS2+qRnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ff29b764638d6c15cbad471a2685f222c0de3fa97ecbbfa95bf3777378f9562","last_reissued_at":"2026-05-17T23:46:37.596251Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:37.596251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.03501","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":"2026-05-17T23:46:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+9e0S+ftd7ZuZ7OTTt1VWvnoL1hAB+sJovOtrmkbBzVoZZxE7Af0kIfAGvXYdIDyBDyStdZzP4qtIF03thdBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T15:30:40.073551Z"},"content_sha256":"a8cf72a472ac76c286cdc8c34cd92ac0d5277ac2eb7f452ffdfb24cf26f7b06b","schema_version":"1.0","event_id":"sha256:a8cf72a472ac76c286cdc8c34cd92ac0d5277ac2eb7f452ffdfb24cf26f7b06b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:J7ZJW5SGHDLMCXF22RY2E2C7EI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pretrain Soft Q-Learning with Imperfect Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Huimin Ma, Xiaoqin Zhang, Xiong Luo, Yunfei Li","submitted_at":"2019-05-09T09:23:53Z","abstract_excerpt":"Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent on online simulations with existing reinforcement learning algorithms. Pretraining reinforcement learning remains a significant challenge in exploiting expert demonstrations whilst keeping exploration potentials, especially for value based methods. In this paper, we propose a pretraining method for soft Q-learning. Our work is inspired by pretraining methods for actor-critic algorithms since soft Q-learning is a val"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03501","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":"2026-05-17T23:46:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D64cRl3grj7gnnxn2Gci/BUmzOtd+CVpeTIDOCHfPIIUrOUFH8yxc1zP1JRnKLvM4dJkEeEEsnWlqV85r32SDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T15:30:40.073927Z"},"content_sha256":"5c97c99c9d588c9cd46f155caf36a036f78bef30f5e22815e814ec691dc1ea05","schema_version":"1.0","event_id":"sha256:5c97c99c9d588c9cd46f155caf36a036f78bef30f5e22815e814ec691dc1ea05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J7ZJW5SGHDLMCXF22RY2E2C7EI/bundle.json","state_url":"https://pith.science/pith/J7ZJW5SGHDLMCXF22RY2E2C7EI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J7ZJW5SGHDLMCXF22RY2E2C7EI/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":"2026-06-01T15:30:40Z","links":{"resolver":"https://pith.science/pith/J7ZJW5SGHDLMCXF22RY2E2C7EI","bundle":"https://pith.science/pith/J7ZJW5SGHDLMCXF22RY2E2C7EI/bundle.json","state":"https://pith.science/pith/J7ZJW5SGHDLMCXF22RY2E2C7EI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J7ZJW5SGHDLMCXF22RY2E2C7EI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:J7ZJW5SGHDLMCXF22RY2E2C7EI","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":"9c547e17c480f63f0eec97cf64577c22844a720057aaad1514fbc46bad6d5769","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-09T09:23:53Z","title_canon_sha256":"f198e5487868ff86973eb251bf6c8bfcdd0a968e3b389582503a2553d07680e8"},"schema_version":"1.0","source":{"id":"1905.03501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.03501","created_at":"2026-05-17T23:46:37Z"},{"alias_kind":"arxiv_version","alias_value":"1905.03501v1","created_at":"2026-05-17T23:46:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03501","created_at":"2026-05-17T23:46:37Z"},{"alias_kind":"pith_short_12","alias_value":"J7ZJW5SGHDLM","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"J7ZJW5SGHDLMCXF2","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"J7ZJW5SG","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:5c97c99c9d588c9cd46f155caf36a036f78bef30f5e22815e814ec691dc1ea05","target":"graph","created_at":"2026-05-17T23:46:37Z","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":"Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent on online simulations with existing reinforcement learning algorithms. Pretraining reinforcement learning remains a significant challenge in exploiting expert demonstrations whilst keeping exploration potentials, especially for value based methods. In this paper, we propose a pretraining method for soft Q-learning. Our work is inspired by pretraining methods for actor-critic algorithms since soft Q-learning is a val","authors_text":"Huimin Ma, Xiaoqin Zhang, Xiong Luo, Yunfei Li","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-09T09:23:53Z","title":"Pretrain Soft Q-Learning with Imperfect Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03501","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:a8cf72a472ac76c286cdc8c34cd92ac0d5277ac2eb7f452ffdfb24cf26f7b06b","target":"record","created_at":"2026-05-17T23:46:37Z","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":"9c547e17c480f63f0eec97cf64577c22844a720057aaad1514fbc46bad6d5769","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-09T09:23:53Z","title_canon_sha256":"f198e5487868ff86973eb251bf6c8bfcdd0a968e3b389582503a2553d07680e8"},"schema_version":"1.0","source":{"id":"1905.03501","kind":"arxiv","version":1}},"canonical_sha256":"4ff29b764638d6c15cbad471a2685f222c0de3fa97ecbbfa95bf3777378f9562","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ff29b764638d6c15cbad471a2685f222c0de3fa97ecbbfa95bf3777378f9562","first_computed_at":"2026-05-17T23:46:37.596251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:37.596251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rWxMDhz0ZGVG3neaIIjjyegKrXZh0jbeEBFnDmwdA2dpD45nOwa8o9WYtzUoxls+5Xy+7xwFbNSTCDS2+qRnCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:37.596912Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.03501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8cf72a472ac76c286cdc8c34cd92ac0d5277ac2eb7f452ffdfb24cf26f7b06b","sha256:5c97c99c9d588c9cd46f155caf36a036f78bef30f5e22815e814ec691dc1ea05"],"state_sha256":"8f2b117e057a21cfdf88132271ab60a58256dd1eba0a9889e934db7c01a1d9ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z9uAT69EcrQ29slMf+Ogye2wXgfOeNXJc4+duDxxsqKTDW3+Q+fkgXt+Qa0AzETaIjYH1uChL5vjSW1z20zCDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T15:30:40.075821Z","bundle_sha256":"a09d1bb7d4a5c085f3e7ad51d98ad2094a037307bd26849b49ccdcad796f8dbe"}}