{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IPY3B3PSPWM7N5RE3HHHNXKH3G","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":"4e5ebd699839f2a5ebaed6c025d5340ec6ee5eaee5232c47252a5e6c11d2559e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-15T03:26:47Z","title_canon_sha256":"c4621b7d9225355e9bcd1cde0cc5200c36364467d722e80523459571ca4cf02c"},"schema_version":"1.0","source":{"id":"2010.07494","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.07494","created_at":"2026-07-05T01:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"2010.07494v2","created_at":"2026-07-05T01:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07494","created_at":"2026-07-05T01:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"IPY3B3PSPWM7","created_at":"2026-07-05T01:43:29Z"},{"alias_kind":"pith_short_16","alias_value":"IPY3B3PSPWM7N5RE","created_at":"2026-07-05T01:43:29Z"},{"alias_kind":"pith_short_8","alias_value":"IPY3B3PS","created_at":"2026-07-05T01:43:29Z"}],"graph_snapshots":[{"event_id":"sha256:b65e25fe0832879d87c610dac7e770eea9c753c66a1b83ed921c9a701eeca345","target":"graph","created_at":"2026-07-05T01:43:29Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.07494/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Deep Reinforcement Learning (DRL) has emerged as a promising approach to many complex tasks, it remains challenging to train a single DRL agent that is capable of undertaking multiple different continuous control tasks. In this paper, we present a Knowledge Transfer based Multi-task Deep Reinforcement Learning framework (KTM-DRL) for continuous control, which enables a single DRL agent to achieve expert-level performance in multiple different tasks by learning from task-specific teachers. In KTM-DRL, the multi-task agent first leverages an offline knowledge transfer algorithm designed pa","authors_text":"Jian Tang, Jieping Ye, Kun Wu, Zhengping Che, Zhiyuan Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-15T03:26:47Z","title":"Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07494","kind":"arxiv","version":2},"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:f78d1f3b50a53fa2038d6724c9f7523a9d22afe717bef77c65c5f11efcbd6108","target":"record","created_at":"2026-07-05T01:43:29Z","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":"4e5ebd699839f2a5ebaed6c025d5340ec6ee5eaee5232c47252a5e6c11d2559e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-15T03:26:47Z","title_canon_sha256":"c4621b7d9225355e9bcd1cde0cc5200c36364467d722e80523459571ca4cf02c"},"schema_version":"1.0","source":{"id":"2010.07494","kind":"arxiv","version":2}},"canonical_sha256":"43f1b0edf27d99f6f624d9ce76dd47d9ba46fc32ecee3d65b59c0565218343e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43f1b0edf27d99f6f624d9ce76dd47d9ba46fc32ecee3d65b59c0565218343e3","first_computed_at":"2026-07-05T01:43:29.038328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:29.038328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rjRmzyUzCwW5XrquHJgjk77I6bTmmSaH77CgD3GN15iwYq5F8tl++Jpt34DGm6RUi2eLuam63Yl82Dxv0FGTBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:29.038881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.07494","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f78d1f3b50a53fa2038d6724c9f7523a9d22afe717bef77c65c5f11efcbd6108","sha256:b65e25fe0832879d87c610dac7e770eea9c753c66a1b83ed921c9a701eeca345"],"state_sha256":"a47c82499edb1ba2e4721326a80db5963c5198e2473c28c51b077621b413abb7"}