{"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"}