{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CWHXZS5QDTM5HI7NEQFIFYYGYI","short_pith_number":"pith:CWHXZS5Q","canonical_record":{"source":{"id":"2210.09646","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-10-18T07:32:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8b77bb311310cff1ea69fe5cb60afdda7e3f79db8e52c3992b209c0cd8fa6731","abstract_canon_sha256":"7c81b03166fab2d35b4ca8ebaa642ec261db57c79ce13c156d05a39e2d5880d5"},"schema_version":"1.0"},"canonical_sha256":"158f7ccbb01cd9d3a3ed240a82e306c238da9411e4e5a4bfbd00641a57705989","source":{"kind":"arxiv","id":"2210.09646","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09646","created_at":"2026-07-05T05:07:57Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09646v1","created_at":"2026-07-05T05:07:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09646","created_at":"2026-07-05T05:07:57Z"},{"alias_kind":"pith_short_12","alias_value":"CWHXZS5QDTM5","created_at":"2026-07-05T05:07:57Z"},{"alias_kind":"pith_short_16","alias_value":"CWHXZS5QDTM5HI7N","created_at":"2026-07-05T05:07:57Z"},{"alias_kind":"pith_short_8","alias_value":"CWHXZS5Q","created_at":"2026-07-05T05:07:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CWHXZS5QDTM5HI7NEQFIFYYGYI","target":"record","payload":{"canonical_record":{"source":{"id":"2210.09646","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-10-18T07:32:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8b77bb311310cff1ea69fe5cb60afdda7e3f79db8e52c3992b209c0cd8fa6731","abstract_canon_sha256":"7c81b03166fab2d35b4ca8ebaa642ec261db57c79ce13c156d05a39e2d5880d5"},"schema_version":"1.0"},"canonical_sha256":"158f7ccbb01cd9d3a3ed240a82e306c238da9411e4e5a4bfbd00641a57705989","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:57.871352Z","signature_b64":"sx5x7zeIcdW1XEF/+2gOzlJ4iin2Nt3GJ86F0PmKSEoehZmaX/C7iHbS6et7U1w2ckH87NX9d0x81svJRrP/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"158f7ccbb01cd9d3a3ed240a82e306c238da9411e4e5a4bfbd00641a57705989","last_reissued_at":"2026-07-05T05:07:57.870959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:57.870959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.09646","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":"2026-07-05T05:07:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eGp3Zg46VfMgDqW5R9u1vHkrr1akJMGfuLKIrMwU9GQibo2lEkl+4Vg7X3kQtXl4w6n6RGV0qNndVaTbDUm6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T21:45:02.856926Z"},"content_sha256":"9fcbbf5c5e66261b7476acb33dba62bf053c334fa3bf3d62e9501d3e87076a98","schema_version":"1.0","event_id":"sha256:9fcbbf5c5e66261b7476acb33dba62bf053c334fa3bf3d62e9501d3e87076a98"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CWHXZS5QDTM5HI7NEQFIFYYGYI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RPM: Generalizable Behaviors for 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, Shuicheng Yan, Svetlana Obraztsova, Wei Qiu, Xiao Ma, Zhongwen Xu","submitted_at":"2022-10-18T07:32:43Z","abstract_excerpt":"Despite the recent advancement in multi-agent reinforcement learning (MARL), the MARL agents easily overfit the training environment and perform poorly in the evaluation scenarios where other agents behave differently. Obtaining generalizable policies for MARL agents is thus necessary but challenging mainly due to complex multi-agent interactions. In this work, we model the problem with Markov Games and propose a simple yet effective method, ranked policy memory (RPM), to collect diverse multi-agent trajectories for training MARL policies with good generalizability. The main idea of RPM is to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09646","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.09646/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":"2026-07-05T05:07:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"77JUVm/zWeEE08b5p0LNZ6JjIhb3jsHO5NXDzuQzE3M3oiilAAuueJAYWioUN0hE7Tw9Iym4lNMERkVjbQPjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T21:45:02.857301Z"},"content_sha256":"9460f65a3c6537bf651648359f8fe659e4dad61b0fe69edb8eaa37c4c2e929fe","schema_version":"1.0","event_id":"sha256:9460f65a3c6537bf651648359f8fe659e4dad61b0fe69edb8eaa37c4c2e929fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CWHXZS5QDTM5HI7NEQFIFYYGYI/bundle.json","state_url":"https://pith.science/pith/CWHXZS5QDTM5HI7NEQFIFYYGYI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CWHXZS5QDTM5HI7NEQFIFYYGYI/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":"2026-07-14T21:45:02Z","links":{"resolver":"https://pith.science/pith/CWHXZS5QDTM5HI7NEQFIFYYGYI","bundle":"https://pith.science/pith/CWHXZS5QDTM5HI7NEQFIFYYGYI/bundle.json","state":"https://pith.science/pith/CWHXZS5QDTM5HI7NEQFIFYYGYI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CWHXZS5QDTM5HI7NEQFIFYYGYI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CWHXZS5QDTM5HI7NEQFIFYYGYI","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":"7c81b03166fab2d35b4ca8ebaa642ec261db57c79ce13c156d05a39e2d5880d5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-10-18T07:32:43Z","title_canon_sha256":"8b77bb311310cff1ea69fe5cb60afdda7e3f79db8e52c3992b209c0cd8fa6731"},"schema_version":"1.0","source":{"id":"2210.09646","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09646","created_at":"2026-07-05T05:07:57Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09646v1","created_at":"2026-07-05T05:07:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09646","created_at":"2026-07-05T05:07:57Z"},{"alias_kind":"pith_short_12","alias_value":"CWHXZS5QDTM5","created_at":"2026-07-05T05:07:57Z"},{"alias_kind":"pith_short_16","alias_value":"CWHXZS5QDTM5HI7N","created_at":"2026-07-05T05:07:57Z"},{"alias_kind":"pith_short_8","alias_value":"CWHXZS5Q","created_at":"2026-07-05T05:07:57Z"}],"graph_snapshots":[{"event_id":"sha256:9460f65a3c6537bf651648359f8fe659e4dad61b0fe69edb8eaa37c4c2e929fe","target":"graph","created_at":"2026-07-05T05:07:57Z","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/2210.09646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the recent advancement in multi-agent reinforcement learning (MARL), the MARL agents easily overfit the training environment and perform poorly in the evaluation scenarios where other agents behave differently. Obtaining generalizable policies for MARL agents is thus necessary but challenging mainly due to complex multi-agent interactions. In this work, we model the problem with Markov Games and propose a simple yet effective method, ranked policy memory (RPM), to collect diverse multi-agent trajectories for training MARL policies with good generalizability. The main idea of RPM is to ","authors_text":"Bo An, Shuicheng Yan, Svetlana Obraztsova, Wei Qiu, Xiao Ma, Zhongwen Xu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-10-18T07:32:43Z","title":"RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09646","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":"sha256:9fcbbf5c5e66261b7476acb33dba62bf053c334fa3bf3d62e9501d3e87076a98","target":"record","created_at":"2026-07-05T05:07:57Z","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":"7c81b03166fab2d35b4ca8ebaa642ec261db57c79ce13c156d05a39e2d5880d5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-10-18T07:32:43Z","title_canon_sha256":"8b77bb311310cff1ea69fe5cb60afdda7e3f79db8e52c3992b209c0cd8fa6731"},"schema_version":"1.0","source":{"id":"2210.09646","kind":"arxiv","version":1}},"canonical_sha256":"158f7ccbb01cd9d3a3ed240a82e306c238da9411e4e5a4bfbd00641a57705989","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"158f7ccbb01cd9d3a3ed240a82e306c238da9411e4e5a4bfbd00641a57705989","first_computed_at":"2026-07-05T05:07:57.870959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:57.870959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sx5x7zeIcdW1XEF/+2gOzlJ4iin2Nt3GJ86F0PmKSEoehZmaX/C7iHbS6et7U1w2ckH87NX9d0x81svJRrP/BA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:57.871352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.09646","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fcbbf5c5e66261b7476acb33dba62bf053c334fa3bf3d62e9501d3e87076a98","sha256:9460f65a3c6537bf651648359f8fe659e4dad61b0fe69edb8eaa37c4c2e929fe"],"state_sha256":"6261ace7721b3d5899edf12febb6ac72481d2e57fae77034b7d57f2893581b18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"03j/gAjdZbcOkF7TznsHqGklCSmSaqL5YjGfkCHlS+aHhyUydTCEV5WYBwaRguEn+GRgjeZHD7SGTe0WMitvDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T21:45:02.859506Z","bundle_sha256":"e6dafea8a388dd8b387b79aaf5f2d7e4eff7f0b3476a1c8c3de5647eae365bf6"}}