{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IX2GF3QHSACR2X2III7X5D2ZN4","short_pith_number":"pith:IX2GF3QH","canonical_record":{"source":{"id":"2002.08030","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-02-19T07:01:38Z","cross_cats_sorted":[],"title_canon_sha256":"137830fa05c092fca93202f5683ac9440dec449423df0b74a61a0047e842708c","abstract_canon_sha256":"697f6d764d3a94cc04d3f80b3a79dbe9db95e5e506799c1eb10a633ffb867aac"},"schema_version":"1.0"},"canonical_sha256":"45f462ee0790051d5f48423f7e8f596f0f05cb052a9d13cf5282d2bbdaea0616","source":{"kind":"arxiv","id":"2002.08030","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.08030","created_at":"2026-07-05T03:26:36Z"},{"alias_kind":"arxiv_version","alias_value":"2002.08030v4","created_at":"2026-07-05T03:26:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.08030","created_at":"2026-07-05T03:26:36Z"},{"alias_kind":"pith_short_12","alias_value":"IX2GF3QHSACR","created_at":"2026-07-05T03:26:36Z"},{"alias_kind":"pith_short_16","alias_value":"IX2GF3QHSACR2X2I","created_at":"2026-07-05T03:26:36Z"},{"alias_kind":"pith_short_8","alias_value":"IX2GF3QH","created_at":"2026-07-05T03:26:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IX2GF3QHSACR2X2III7X5D2ZN4","target":"record","payload":{"canonical_record":{"source":{"id":"2002.08030","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-02-19T07:01:38Z","cross_cats_sorted":[],"title_canon_sha256":"137830fa05c092fca93202f5683ac9440dec449423df0b74a61a0047e842708c","abstract_canon_sha256":"697f6d764d3a94cc04d3f80b3a79dbe9db95e5e506799c1eb10a633ffb867aac"},"schema_version":"1.0"},"canonical_sha256":"45f462ee0790051d5f48423f7e8f596f0f05cb052a9d13cf5282d2bbdaea0616","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:36.405909Z","signature_b64":"23nOQduqJ5oH3gIL/fMYNhYUDPcCzJ2Jg8sn5rYe95iZwJZ4klN8CFIyzOZgRu7YAdhDiv0gJoVU50+s4T2YAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45f462ee0790051d5f48423f7e8f596f0f05cb052a9d13cf5282d2bbdaea0616","last_reissued_at":"2026-07-05T03:26:36.405418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:36.405418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.08030","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:26:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wpjaVnrxkbiglhOxJwiGMuvVaWwn4s5D9LPrHWTr4HVWzsqQ7A8rjdno/iEPgnFW3vwrNqh0QNtBK9wbU0znAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:45:51.662052Z"},"content_sha256":"aca789fad1c3b5f7f27a4c01f914ae21b0e88a3403cdaf441e6fc211dcb94c26","schema_version":"1.0","event_id":"sha256:aca789fad1c3b5f7f27a4c01f914ae21b0e88a3403cdaf441e6fc211dcb94c26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IX2GF3QHSACR2X2III7X5D2ZN4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Changjie Fan, Chengwei Zhang, Dong Li, Hangyu Mao, Hongyao Tang, Jianye Hao, Tianpei Yang, Weixun Wang, Wulong Liu, Yingfeng Chen, Yujing Hu, Zhaopeng Meng","submitted_at":"2020-02-19T07:01:38Z","abstract_excerpt":"Transfer Learning has shown great potential to enhance single-agent Reinforcement Learning (RL) efficiency. Similarly, Multiagent RL (MARL) can also be accelerated if agents can share knowledge with each other. However, it remains a problem of how an agent should learn from other agents. In this paper, we propose a novel Multiagent Policy Transfer Framework (MAPTF) to improve MARL efficiency. MAPTF learns which agent's policy is the best to reuse for each agent and when to terminate it by modeling multiagent policy transfer as the option learning problem. Furthermore, in practice, the option m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.08030","kind":"arxiv","version":4},"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/2002.08030/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:26:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7/bfuaNS3ViZ+i5BEbB9HupFDaSYkGp70e07tgoeYm7+aRy3bN733q27KX/qE247SGRlZtEixltD9b2jT0iyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:45:51.662453Z"},"content_sha256":"77dd9dad5cb96985e5d297de4f266f4bac486632f4bd820c08c1b1d136673cfa","schema_version":"1.0","event_id":"sha256:77dd9dad5cb96985e5d297de4f266f4bac486632f4bd820c08c1b1d136673cfa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IX2GF3QHSACR2X2III7X5D2ZN4/bundle.json","state_url":"https://pith.science/pith/IX2GF3QHSACR2X2III7X5D2ZN4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IX2GF3QHSACR2X2III7X5D2ZN4/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":"2026-07-08T13:45:51Z","links":{"resolver":"https://pith.science/pith/IX2GF3QHSACR2X2III7X5D2ZN4","bundle":"https://pith.science/pith/IX2GF3QHSACR2X2III7X5D2ZN4/bundle.json","state":"https://pith.science/pith/IX2GF3QHSACR2X2III7X5D2ZN4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IX2GF3QHSACR2X2III7X5D2ZN4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IX2GF3QHSACR2X2III7X5D2ZN4","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":"697f6d764d3a94cc04d3f80b3a79dbe9db95e5e506799c1eb10a633ffb867aac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-02-19T07:01:38Z","title_canon_sha256":"137830fa05c092fca93202f5683ac9440dec449423df0b74a61a0047e842708c"},"schema_version":"1.0","source":{"id":"2002.08030","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.08030","created_at":"2026-07-05T03:26:36Z"},{"alias_kind":"arxiv_version","alias_value":"2002.08030v4","created_at":"2026-07-05T03:26:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.08030","created_at":"2026-07-05T03:26:36Z"},{"alias_kind":"pith_short_12","alias_value":"IX2GF3QHSACR","created_at":"2026-07-05T03:26:36Z"},{"alias_kind":"pith_short_16","alias_value":"IX2GF3QHSACR2X2I","created_at":"2026-07-05T03:26:36Z"},{"alias_kind":"pith_short_8","alias_value":"IX2GF3QH","created_at":"2026-07-05T03:26:36Z"}],"graph_snapshots":[{"event_id":"sha256:77dd9dad5cb96985e5d297de4f266f4bac486632f4bd820c08c1b1d136673cfa","target":"graph","created_at":"2026-07-05T03:26:36Z","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/2002.08030/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transfer Learning has shown great potential to enhance single-agent Reinforcement Learning (RL) efficiency. Similarly, Multiagent RL (MARL) can also be accelerated if agents can share knowledge with each other. However, it remains a problem of how an agent should learn from other agents. In this paper, we propose a novel Multiagent Policy Transfer Framework (MAPTF) to improve MARL efficiency. MAPTF learns which agent's policy is the best to reuse for each agent and when to terminate it by modeling multiagent policy transfer as the option learning problem. Furthermore, in practice, the option m","authors_text":"Changjie Fan, Chengwei Zhang, Dong Li, Hangyu Mao, Hongyao Tang, Jianye Hao, Tianpei Yang, Weixun Wang, Wulong Liu, Yingfeng Chen, Yujing Hu, Zhaopeng Meng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-02-19T07:01:38Z","title":"An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.08030","kind":"arxiv","version":4},"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:aca789fad1c3b5f7f27a4c01f914ae21b0e88a3403cdaf441e6fc211dcb94c26","target":"record","created_at":"2026-07-05T03:26:36Z","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":"697f6d764d3a94cc04d3f80b3a79dbe9db95e5e506799c1eb10a633ffb867aac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-02-19T07:01:38Z","title_canon_sha256":"137830fa05c092fca93202f5683ac9440dec449423df0b74a61a0047e842708c"},"schema_version":"1.0","source":{"id":"2002.08030","kind":"arxiv","version":4}},"canonical_sha256":"45f462ee0790051d5f48423f7e8f596f0f05cb052a9d13cf5282d2bbdaea0616","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45f462ee0790051d5f48423f7e8f596f0f05cb052a9d13cf5282d2bbdaea0616","first_computed_at":"2026-07-05T03:26:36.405418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:36.405418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"23nOQduqJ5oH3gIL/fMYNhYUDPcCzJ2Jg8sn5rYe95iZwJZ4klN8CFIyzOZgRu7YAdhDiv0gJoVU50+s4T2YAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:36.405909Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.08030","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aca789fad1c3b5f7f27a4c01f914ae21b0e88a3403cdaf441e6fc211dcb94c26","sha256:77dd9dad5cb96985e5d297de4f266f4bac486632f4bd820c08c1b1d136673cfa"],"state_sha256":"00115277a4a6ff3243d3f7426f9ea110b2a6f9e59ddfe40ffa7950e0df289aca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sPkNOsPJL3t4AIQRrqK9Yjq+qi1iIaFdX83jb+esFP4kKvWSGhDRxzCPQZ0xBYwj34oNor1kHjLNcV6ea7WVDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T13:45:51.665086Z","bundle_sha256":"addd48c23c57f193590f0acf1dc1871195d27fa2b62710eea4ad77d8733b4884"}}