{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:H4FGSMKYRM5M3YBPYIQXBLHO3Q","short_pith_number":"pith:H4FGSMKY","canonical_record":{"source":{"id":"1811.07029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T11:30:29Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"0f1d9d78d9d900e1ba255deace00f62e084a583555aa5cff7b646ffa4632e794","abstract_canon_sha256":"4a8326afcaec7f9dfef2523a04338cd5e3f8820a14b036df8065f9421a2f0388"},"schema_version":"1.0"},"canonical_sha256":"3f0a6931588b3acde02fc22170aceedc22e48a9959855eea2b53375bc9fb165c","source":{"kind":"arxiv","id":"1811.07029","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.07029","created_at":"2026-05-18T00:00:29Z"},{"alias_kind":"arxiv_version","alias_value":"1811.07029v1","created_at":"2026-05-18T00:00:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07029","created_at":"2026-05-18T00:00:29Z"},{"alias_kind":"pith_short_12","alias_value":"H4FGSMKYRM5M","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H4FGSMKYRM5M3YBP","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H4FGSMKY","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:H4FGSMKYRM5M3YBPYIQXBLHO3Q","target":"record","payload":{"canonical_record":{"source":{"id":"1811.07029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T11:30:29Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"0f1d9d78d9d900e1ba255deace00f62e084a583555aa5cff7b646ffa4632e794","abstract_canon_sha256":"4a8326afcaec7f9dfef2523a04338cd5e3f8820a14b036df8065f9421a2f0388"},"schema_version":"1.0"},"canonical_sha256":"3f0a6931588b3acde02fc22170aceedc22e48a9959855eea2b53375bc9fb165c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:29.244875Z","signature_b64":"fJZcSrEb4pJUOhrUvHdL0LiJdLSvxAC/D+4k7q+zljEL6OGDctjf5uhdQ2v2Cjp0JtRfENZRhpqEShoTIcQ5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f0a6931588b3acde02fc22170aceedc22e48a9959855eea2b53375bc9fb165c","last_reissued_at":"2026-05-18T00:00:29.244174Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:29.244174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.07029","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":"2026-05-18T00:00:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qQyoEjAKVBTr3qAHtT+H4erZ2WL5zqyMUyfv5SFnUeircgQuWKmor/MNa+9HmLx4q5mC0D/K5TYusJcd901fCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:59:05.836644Z"},"content_sha256":"67a9076742604e70983c27fd4594986cd057c266a8b6b279279be4c310b7431e","schema_version":"1.0","event_id":"sha256:67a9076742604e70983c27fd4594986cd057c266a8b6b279279be4c310b7431e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:H4FGSMKYRM5M3YBPYIQXBLHO3Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPG","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hangyu Mao, Zhengchao Zhang, Zhen Xiao, Zhibo Gong","submitted_at":"2018-11-13T11:30:29Z","abstract_excerpt":"Modelling and exploiting teammates' policies in cooperative multi-agent systems have long been an interest and also a big challenge for the reinforcement learning (RL) community. The interest lies in the fact that if the agent knows the teammates' policies, it can adjust its own policy accordingly to arrive at proper cooperations; while the challenge is that the agents' policies are changing continuously due to they are learning concurrently, which imposes difficulty to model the dynamic policies of teammates accurately. In this paper, we present \\emph{ATTention Multi-Agent Deep Deterministic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07029","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":"2026-05-18T00:00:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dzh2BI0orm54iBTRmS2/ZiR2+6zCSEIFT8SzRxk/uQluOpMFlY6VbrPWZe3O23s07h0i629P9/XJcxxox0bqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:59:05.837009Z"},"content_sha256":"0b90b7e76b6d3d038327a7b8fa5af06b10c7f1ea5efab8e51aea26a0331c36fd","schema_version":"1.0","event_id":"sha256:0b90b7e76b6d3d038327a7b8fa5af06b10c7f1ea5efab8e51aea26a0331c36fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q/bundle.json","state_url":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q/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":"2026-05-27T14:59:05Z","links":{"resolver":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q","bundle":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q/bundle.json","state":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:H4FGSMKYRM5M3YBPYIQXBLHO3Q","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":"4a8326afcaec7f9dfef2523a04338cd5e3f8820a14b036df8065f9421a2f0388","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T11:30:29Z","title_canon_sha256":"0f1d9d78d9d900e1ba255deace00f62e084a583555aa5cff7b646ffa4632e794"},"schema_version":"1.0","source":{"id":"1811.07029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.07029","created_at":"2026-05-18T00:00:29Z"},{"alias_kind":"arxiv_version","alias_value":"1811.07029v1","created_at":"2026-05-18T00:00:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07029","created_at":"2026-05-18T00:00:29Z"},{"alias_kind":"pith_short_12","alias_value":"H4FGSMKYRM5M","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H4FGSMKYRM5M3YBP","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H4FGSMKY","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:0b90b7e76b6d3d038327a7b8fa5af06b10c7f1ea5efab8e51aea26a0331c36fd","target":"graph","created_at":"2026-05-18T00:00:29Z","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"},"paper":{"abstract_excerpt":"Modelling and exploiting teammates' policies in cooperative multi-agent systems have long been an interest and also a big challenge for the reinforcement learning (RL) community. The interest lies in the fact that if the agent knows the teammates' policies, it can adjust its own policy accordingly to arrive at proper cooperations; while the challenge is that the agents' policies are changing continuously due to they are learning concurrently, which imposes difficulty to model the dynamic policies of teammates accurately. In this paper, we present \\emph{ATTention Multi-Agent Deep Deterministic ","authors_text":"Hangyu Mao, Zhengchao Zhang, Zhen Xiao, Zhibo Gong","cross_cats":["cs.AI","cs.MA","stat.ML"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T11:30:29Z","title":"Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPG"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07029","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":"sha256:67a9076742604e70983c27fd4594986cd057c266a8b6b279279be4c310b7431e","target":"record","created_at":"2026-05-18T00:00:29Z","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":"4a8326afcaec7f9dfef2523a04338cd5e3f8820a14b036df8065f9421a2f0388","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T11:30:29Z","title_canon_sha256":"0f1d9d78d9d900e1ba255deace00f62e084a583555aa5cff7b646ffa4632e794"},"schema_version":"1.0","source":{"id":"1811.07029","kind":"arxiv","version":1}},"canonical_sha256":"3f0a6931588b3acde02fc22170aceedc22e48a9959855eea2b53375bc9fb165c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f0a6931588b3acde02fc22170aceedc22e48a9959855eea2b53375bc9fb165c","first_computed_at":"2026-05-18T00:00:29.244174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:29.244174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fJZcSrEb4pJUOhrUvHdL0LiJdLSvxAC/D+4k7q+zljEL6OGDctjf5uhdQ2v2Cjp0JtRfENZRhpqEShoTIcQ5Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:29.244875Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.07029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67a9076742604e70983c27fd4594986cd057c266a8b6b279279be4c310b7431e","sha256:0b90b7e76b6d3d038327a7b8fa5af06b10c7f1ea5efab8e51aea26a0331c36fd"],"state_sha256":"eaa3aa6b5906027f7116c6a47bac71903afc0feef8b7b552bbfccb08820ce2c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dO+zXTgT9mr3gzdk3NO8Q01KHhbC8kheKzVQW5KIH97qZfL2KR9Fblk+2ezY0DdCRUBWaKP4ulXfi66p018WBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:59:05.839793Z","bundle_sha256":"ad0fdc09b22f76d60e08d6cdd136d5fc29f6c6057561aa52af5a31d712b10b5e"}}