{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IPY3B3PSPWM7N5RE3HHHNXKH3G","short_pith_number":"pith:IPY3B3PS","schema_version":"1.0","canonical_sha256":"43f1b0edf27d99f6f624d9ce76dd47d9ba46fc32ecee3d65b59c0565218343e3","source":{"kind":"arxiv","id":"2010.07494","version":2},"attestation_state":"computed","paper":{"title":"Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jian Tang, Jieping Ye, Kun Wu, Zhengping Che, Zhiyuan Xu","submitted_at":"2020-10-15T03:26:47Z","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"},"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":"2010.07494","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-15T03:26:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4621b7d9225355e9bcd1cde0cc5200c36364467d722e80523459571ca4cf02c","abstract_canon_sha256":"4e5ebd699839f2a5ebaed6c025d5340ec6ee5eaee5232c47252a5e6c11d2559e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:29.038881Z","signature_b64":"rjRmzyUzCwW5XrquHJgjk77I6bTmmSaH77CgD3GN15iwYq5F8tl++Jpt34DGm6RUi2eLuam63Yl82Dxv0FGTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43f1b0edf27d99f6f624d9ce76dd47d9ba46fc32ecee3d65b59c0565218343e3","last_reissued_at":"2026-07-05T01:43:29.038328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:29.038328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jian Tang, Jieping Ye, Kun Wu, Zhengping Che, Zhiyuan Xu","submitted_at":"2020-10-15T03:26:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07494","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.07494/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2010.07494","created_at":"2026-07-05T01:43:29.038388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.07494v2","created_at":"2026-07-05T01:43:29.038388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07494","created_at":"2026-07-05T01:43:29.038388+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPY3B3PSPWM7","created_at":"2026-07-05T01:43:29.038388+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPY3B3PSPWM7N5RE","created_at":"2026-07-05T01:43:29.038388+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPY3B3PS","created_at":"2026-07-05T01:43:29.038388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPY3B3PSPWM7N5RE3HHHNXKH3G","json":"https://pith.science/pith/IPY3B3PSPWM7N5RE3HHHNXKH3G.json","graph_json":"https://pith.science/api/pith-number/IPY3B3PSPWM7N5RE3HHHNXKH3G/graph.json","events_json":"https://pith.science/api/pith-number/IPY3B3PSPWM7N5RE3HHHNXKH3G/events.json","paper":"https://pith.science/paper/IPY3B3PS"},"agent_actions":{"view_html":"https://pith.science/pith/IPY3B3PSPWM7N5RE3HHHNXKH3G","download_json":"https://pith.science/pith/IPY3B3PSPWM7N5RE3HHHNXKH3G.json","view_paper":"https://pith.science/paper/IPY3B3PS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.07494&json=true","fetch_graph":"https://pith.science/api/pith-number/IPY3B3PSPWM7N5RE3HHHNXKH3G/graph.json","fetch_events":"https://pith.science/api/pith-number/IPY3B3PSPWM7N5RE3HHHNXKH3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPY3B3PSPWM7N5RE3HHHNXKH3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPY3B3PSPWM7N5RE3HHHNXKH3G/action/storage_attestation","attest_author":"https://pith.science/pith/IPY3B3PSPWM7N5RE3HHHNXKH3G/action/author_attestation","sign_citation":"https://pith.science/pith/IPY3B3PSPWM7N5RE3HHHNXKH3G/action/citation_signature","submit_replication":"https://pith.science/pith/IPY3B3PSPWM7N5RE3HHHNXKH3G/action/replication_record"}},"created_at":"2026-07-05T01:43:29.038388+00:00","updated_at":"2026-07-05T01:43:29.038388+00:00"}