{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:D6AH2MBTWFFKZB3QTFZSUJ4GJJ","short_pith_number":"pith:D6AH2MBT","canonical_record":{"source":{"id":"2205.13718","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-05-27T02:21:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"257777d445f3037af36dd51dcb33ca7f93f85cecd12c9e2ccdbe5ebb0d805dfb","abstract_canon_sha256":"f234a2cb61d161f0241b69544632e5bf5e82de27f73308e95ae82d989592ae3e"},"schema_version":"1.0"},"canonical_sha256":"1f807d3033b14aac877099732a27864a47a65bf95a4e017adf98260d37c89964","source":{"kind":"arxiv","id":"2205.13718","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13718","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13718v2","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13718","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_12","alias_value":"D6AH2MBTWFFK","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_16","alias_value":"D6AH2MBTWFFKZB3Q","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_8","alias_value":"D6AH2MBT","created_at":"2026-07-05T04:33:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:D6AH2MBTWFFKZB3QTFZSUJ4GJJ","target":"record","payload":{"canonical_record":{"source":{"id":"2205.13718","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-05-27T02:21:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"257777d445f3037af36dd51dcb33ca7f93f85cecd12c9e2ccdbe5ebb0d805dfb","abstract_canon_sha256":"f234a2cb61d161f0241b69544632e5bf5e82de27f73308e95ae82d989592ae3e"},"schema_version":"1.0"},"canonical_sha256":"1f807d3033b14aac877099732a27864a47a65bf95a4e017adf98260d37c89964","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:00.267113Z","signature_b64":"U5NrPjSh5BFJ8xwOhmu0OqdlRbmYzf+kYhvNXzz9B31oJJNhXQdKNkyFb5LxhFyir/8tsz0OVLC/dylCniHyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f807d3033b14aac877099732a27864a47a65bf95a4e017adf98260d37c89964","last_reissued_at":"2026-07-05T04:33:00.266681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:00.266681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.13718","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:33:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ieuKgp9rlbiqAo5DbHTNqHFp/rfdLT6uta81JgVqaSQIa2s2kFZ90AgODK9arq74mZWHvlBlidX0z+IggMY6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:26:05.701314Z"},"content_sha256":"229eadfef53bc4717f31bfcd34883afed52821bc9327c3c02e6e9dd2b643c905","schema_version":"1.0","event_id":"sha256:229eadfef53bc4717f31bfcd34883afed52821bc9327c3c02e6e9dd2b643c905"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:D6AH2MBTWFFKZB3QTFZSUJ4GJJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Off-Beat Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Bo An, Changjie Fan, Jianye Hao, Rundong Wang, Svetlana Obraztsova, Wei Qiu, Weixun Wang, Yingfeng Chen, Yujing Hu, Zinovi Rabinovich","submitted_at":"2022-05-27T02:21:04Z","abstract_excerpt":"We investigate model-free multi-agent reinforcement learning (MARL) in environments where off-beat actions are prevalent, i.e., all actions have pre-set execution durations. During execution durations, the environment changes are influenced by, but not synchronised with, action execution. Such a setting is ubiquitous in many real-world problems. However, most MARL methods assume actions are executed immediately after inference, which is often unrealistic and can lead to catastrophic failure for multi-agent coordination with off-beat actions. In order to fill this gap, we develop an algorithmic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13718","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/2205.13718/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":"2026-07-05T04:33:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1bddTFW6AWx9QqGT35tco70GSKD9alDftgpf0DxSlq/TnK+N7sfQ+e8MQMG9oire6IHBhJgyTzg75q4QEWwTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:26:05.701817Z"},"content_sha256":"f72db2b3807455f5a861d30cb82f8c2965b374f2b2ed167d337b833c26876fea","schema_version":"1.0","event_id":"sha256:f72db2b3807455f5a861d30cb82f8c2965b374f2b2ed167d337b833c26876fea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D6AH2MBTWFFKZB3QTFZSUJ4GJJ/bundle.json","state_url":"https://pith.science/pith/D6AH2MBTWFFKZB3QTFZSUJ4GJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D6AH2MBTWFFKZB3QTFZSUJ4GJJ/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":"2026-08-06T01:26:05Z","links":{"resolver":"https://pith.science/pith/D6AH2MBTWFFKZB3QTFZSUJ4GJJ","bundle":"https://pith.science/pith/D6AH2MBTWFFKZB3QTFZSUJ4GJJ/bundle.json","state":"https://pith.science/pith/D6AH2MBTWFFKZB3QTFZSUJ4GJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D6AH2MBTWFFKZB3QTFZSUJ4GJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:D6AH2MBTWFFKZB3QTFZSUJ4GJJ","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":"f234a2cb61d161f0241b69544632e5bf5e82de27f73308e95ae82d989592ae3e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-05-27T02:21:04Z","title_canon_sha256":"257777d445f3037af36dd51dcb33ca7f93f85cecd12c9e2ccdbe5ebb0d805dfb"},"schema_version":"1.0","source":{"id":"2205.13718","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13718","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13718v2","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13718","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_12","alias_value":"D6AH2MBTWFFK","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_16","alias_value":"D6AH2MBTWFFKZB3Q","created_at":"2026-07-05T04:33:00Z"},{"alias_kind":"pith_short_8","alias_value":"D6AH2MBT","created_at":"2026-07-05T04:33:00Z"}],"graph_snapshots":[{"event_id":"sha256:f72db2b3807455f5a861d30cb82f8c2965b374f2b2ed167d337b833c26876fea","target":"graph","created_at":"2026-07-05T04:33:00Z","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/2205.13718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate model-free multi-agent reinforcement learning (MARL) in environments where off-beat actions are prevalent, i.e., all actions have pre-set execution durations. During execution durations, the environment changes are influenced by, but not synchronised with, action execution. Such a setting is ubiquitous in many real-world problems. However, most MARL methods assume actions are executed immediately after inference, which is often unrealistic and can lead to catastrophic failure for multi-agent coordination with off-beat actions. In order to fill this gap, we develop an algorithmic","authors_text":"Bo An, Changjie Fan, Jianye Hao, Rundong Wang, Svetlana Obraztsova, Wei Qiu, Weixun Wang, Yingfeng Chen, Yujing Hu, Zinovi Rabinovich","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-05-27T02:21:04Z","title":"Off-Beat Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13718","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":"sha256:229eadfef53bc4717f31bfcd34883afed52821bc9327c3c02e6e9dd2b643c905","target":"record","created_at":"2026-07-05T04:33:00Z","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":"f234a2cb61d161f0241b69544632e5bf5e82de27f73308e95ae82d989592ae3e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-05-27T02:21:04Z","title_canon_sha256":"257777d445f3037af36dd51dcb33ca7f93f85cecd12c9e2ccdbe5ebb0d805dfb"},"schema_version":"1.0","source":{"id":"2205.13718","kind":"arxiv","version":2}},"canonical_sha256":"1f807d3033b14aac877099732a27864a47a65bf95a4e017adf98260d37c89964","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f807d3033b14aac877099732a27864a47a65bf95a4e017adf98260d37c89964","first_computed_at":"2026-07-05T04:33:00.266681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:33:00.266681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U5NrPjSh5BFJ8xwOhmu0OqdlRbmYzf+kYhvNXzz9B31oJJNhXQdKNkyFb5LxhFyir/8tsz0OVLC/dylCniHyAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:33:00.267113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.13718","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:229eadfef53bc4717f31bfcd34883afed52821bc9327c3c02e6e9dd2b643c905","sha256:f72db2b3807455f5a861d30cb82f8c2965b374f2b2ed167d337b833c26876fea"],"state_sha256":"f95b183b8029547d000e6210b2995fe62576092391804c6451b95f417b6aeaf3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5OUkAqh6hQInN+rVD9mEiUdDGDBR0JiMTUH2ndrnUkoF9lHDxEr8K7X1jLmcKjI3skrFICEyoXkGbrPQJ/oOBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:26:05.706864Z","bundle_sha256":"9e4d2367d60ccae91078860000a6c6a4f0a56a642b620fb34f586250f1316346"}}