{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XPOR4RDWQC7UVAP64N4MWDPU5Z","short_pith_number":"pith:XPOR4RDW","canonical_record":{"source":{"id":"2111.03431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-11-05T12:01:28Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"9a32b090bf67e1390b355d44d01d5c4c8e6dd1e1dfba6cbf657254b50e7e1b59","abstract_canon_sha256":"9ecfc844e1caa5c4f5dfcee559ee4a301496f4977141862490cdcf3c887b5cc4"},"schema_version":"1.0"},"canonical_sha256":"bbdd1e447680bf4a81fee378cb0df4ee7f5d3a9be9ddb7aa7988e7161c577cc8","source":{"kind":"arxiv","id":"2111.03431","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.03431","created_at":"2026-07-05T05:08:25Z"},{"alias_kind":"arxiv_version","alias_value":"2111.03431v1","created_at":"2026-07-05T05:08:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03431","created_at":"2026-07-05T05:08:25Z"},{"alias_kind":"pith_short_12","alias_value":"XPOR4RDWQC7U","created_at":"2026-07-05T05:08:25Z"},{"alias_kind":"pith_short_16","alias_value":"XPOR4RDWQC7UVAP6","created_at":"2026-07-05T05:08:25Z"},{"alias_kind":"pith_short_8","alias_value":"XPOR4RDW","created_at":"2026-07-05T05:08:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XPOR4RDWQC7UVAP64N4MWDPU5Z","target":"record","payload":{"canonical_record":{"source":{"id":"2111.03431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-11-05T12:01:28Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"9a32b090bf67e1390b355d44d01d5c4c8e6dd1e1dfba6cbf657254b50e7e1b59","abstract_canon_sha256":"9ecfc844e1caa5c4f5dfcee559ee4a301496f4977141862490cdcf3c887b5cc4"},"schema_version":"1.0"},"canonical_sha256":"bbdd1e447680bf4a81fee378cb0df4ee7f5d3a9be9ddb7aa7988e7161c577cc8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:25.501916Z","signature_b64":"lxkGRBmSeQ/Jq0NctrWJpaHj6Fc8OWTahICIFkNzuJAZTPqvTTa6/NS6sIsy7Y2ofohySlhQ1QxRp47IS05dBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbdd1e447680bf4a81fee378cb0df4ee7f5d3a9be9ddb7aa7988e7161c577cc8","last_reissued_at":"2026-07-05T05:08:25.501436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:25.501436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.03431","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":"2026-07-05T05:08:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mw3ITs33n9s4RD0N3+VBQjT0UfQu7WPr/Q0tMJuwE/O3yd1faXiPillXSKDjhNYvdTDucUtPuHCwb3iMOND4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:29:28.117121Z"},"content_sha256":"3dd533a7625bb6d58b97eaf1b55b6968b6f94a65c574c678132583a166950f57","schema_version":"1.0","event_id":"sha256:3dd533a7625bb6d58b97eaf1b55b6968b6f94a65c574c678132583a166950f57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XPOR4RDWQC7UVAP64N4MWDPU5Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Cooperate with Unseen Agent via Meta-Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Nat Dilokthanakul, Poramate Manoonpong, Rujikorn Charakorn","submitted_at":"2021-11-05T12:01:28Z","abstract_excerpt":"Ad hoc teamwork problem describes situations where an agent has to cooperate with previously unseen agents to achieve a common goal. For an agent to be successful in these scenarios, it has to have a suitable cooperative skill. One could implement cooperative skills into an agent by using domain knowledge to design the agent's behavior. However, in complex domains, domain knowledge might not be available. Therefore, it is worthwhile to explore how to directly learn cooperative skills from data. In this work, we apply meta-reinforcement learning (meta-RL) formulation in the context of the ad ho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03431","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/2111.03431/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":"2026-07-05T05:08:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fS8PCOXovdciVbkyA+38KYWBEuRxQlt02XJRtQwwyJOeyAvjLSN5tvb0aWLbvieVvDDxkYlaDc6kFqlWtPnTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:29:28.117622Z"},"content_sha256":"4a4c0fb0ac211c683b15266405a26a65bf482e38fb341403782d6502885c42e7","schema_version":"1.0","event_id":"sha256:4a4c0fb0ac211c683b15266405a26a65bf482e38fb341403782d6502885c42e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XPOR4RDWQC7UVAP64N4MWDPU5Z/bundle.json","state_url":"https://pith.science/pith/XPOR4RDWQC7UVAP64N4MWDPU5Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XPOR4RDWQC7UVAP64N4MWDPU5Z/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":"2026-08-10T09:29:28Z","links":{"resolver":"https://pith.science/pith/XPOR4RDWQC7UVAP64N4MWDPU5Z","bundle":"https://pith.science/pith/XPOR4RDWQC7UVAP64N4MWDPU5Z/bundle.json","state":"https://pith.science/pith/XPOR4RDWQC7UVAP64N4MWDPU5Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XPOR4RDWQC7UVAP64N4MWDPU5Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XPOR4RDWQC7UVAP64N4MWDPU5Z","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":"9ecfc844e1caa5c4f5dfcee559ee4a301496f4977141862490cdcf3c887b5cc4","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-11-05T12:01:28Z","title_canon_sha256":"9a32b090bf67e1390b355d44d01d5c4c8e6dd1e1dfba6cbf657254b50e7e1b59"},"schema_version":"1.0","source":{"id":"2111.03431","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.03431","created_at":"2026-07-05T05:08:25Z"},{"alias_kind":"arxiv_version","alias_value":"2111.03431v1","created_at":"2026-07-05T05:08:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03431","created_at":"2026-07-05T05:08:25Z"},{"alias_kind":"pith_short_12","alias_value":"XPOR4RDWQC7U","created_at":"2026-07-05T05:08:25Z"},{"alias_kind":"pith_short_16","alias_value":"XPOR4RDWQC7UVAP6","created_at":"2026-07-05T05:08:25Z"},{"alias_kind":"pith_short_8","alias_value":"XPOR4RDW","created_at":"2026-07-05T05:08:25Z"}],"graph_snapshots":[{"event_id":"sha256:4a4c0fb0ac211c683b15266405a26a65bf482e38fb341403782d6502885c42e7","target":"graph","created_at":"2026-07-05T05:08:25Z","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/2111.03431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ad hoc teamwork problem describes situations where an agent has to cooperate with previously unseen agents to achieve a common goal. For an agent to be successful in these scenarios, it has to have a suitable cooperative skill. One could implement cooperative skills into an agent by using domain knowledge to design the agent's behavior. However, in complex domains, domain knowledge might not be available. Therefore, it is worthwhile to explore how to directly learn cooperative skills from data. In this work, we apply meta-reinforcement learning (meta-RL) formulation in the context of the ad ho","authors_text":"Nat Dilokthanakul, Poramate Manoonpong, Rujikorn Charakorn","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-11-05T12:01:28Z","title":"Learning to Cooperate with Unseen Agent via Meta-Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03431","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":"sha256:3dd533a7625bb6d58b97eaf1b55b6968b6f94a65c574c678132583a166950f57","target":"record","created_at":"2026-07-05T05:08:25Z","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":"9ecfc844e1caa5c4f5dfcee559ee4a301496f4977141862490cdcf3c887b5cc4","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-11-05T12:01:28Z","title_canon_sha256":"9a32b090bf67e1390b355d44d01d5c4c8e6dd1e1dfba6cbf657254b50e7e1b59"},"schema_version":"1.0","source":{"id":"2111.03431","kind":"arxiv","version":1}},"canonical_sha256":"bbdd1e447680bf4a81fee378cb0df4ee7f5d3a9be9ddb7aa7988e7161c577cc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbdd1e447680bf4a81fee378cb0df4ee7f5d3a9be9ddb7aa7988e7161c577cc8","first_computed_at":"2026-07-05T05:08:25.501436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:25.501436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lxkGRBmSeQ/Jq0NctrWJpaHj6Fc8OWTahICIFkNzuJAZTPqvTTa6/NS6sIsy7Y2ofohySlhQ1QxRp47IS05dBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:25.501916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.03431","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dd533a7625bb6d58b97eaf1b55b6968b6f94a65c574c678132583a166950f57","sha256:4a4c0fb0ac211c683b15266405a26a65bf482e38fb341403782d6502885c42e7"],"state_sha256":"196c668705a6f61587599663e4903d29f97f8cf769660af441ffc7c189916e26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vcBq120c5FpcUfK8l+sNUND39U936KRjarx0ZsqKX7InvKS6LGQjwRPyCq6nUxdTo5cyMg3quBINrKEB/e+zBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:29:28.121585Z","bundle_sha256":"9e132ab23ce1528217edca14ac667044a891728242278ae97c408fd9100fbfcc"}}