{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:X7TXD2RYAQ5W3YJMJMXMVPTIG2","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":"78f97abf04f9e39d61b76280514867b0514ff5522ef58d833cbcc4aed6e79c73","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T18:43:42Z","title_canon_sha256":"7506d8a9c436e0055c1c0b811f80a98be368e5b0e3488f31f5293ecdc29d3f49"},"schema_version":"1.0","source":{"id":"2006.09447","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.09447","created_at":"2026-07-05T03:30:06Z"},{"alias_kind":"arxiv_version","alias_value":"2006.09447v4","created_at":"2026-07-05T03:30:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09447","created_at":"2026-07-05T03:30:06Z"},{"alias_kind":"pith_short_12","alias_value":"X7TXD2RYAQ5W","created_at":"2026-07-05T03:30:06Z"},{"alias_kind":"pith_short_16","alias_value":"X7TXD2RYAQ5W3YJM","created_at":"2026-07-05T03:30:06Z"},{"alias_kind":"pith_short_8","alias_value":"X7TXD2RY","created_at":"2026-07-05T03:30:06Z"}],"graph_snapshots":[{"event_id":"sha256:6808ed8aaff893317f67975583a3c31c0dbbe2d0ed28357d6328bf00935ab7cd","target":"graph","created_at":"2026-07-05T03:30:06Z","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/2006.09447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modelling the behaviours of other agents is essential for understanding how agents interact and making effective decisions. Existing methods for agent modelling commonly assume knowledge of the local observations and chosen actions of the modelled agents during execution. To eliminate this assumption, we extract representations from the local information of the controlled agent using encoder-decoder architectures. Using the observations and actions of the modelled agents during training, our models learn to extract representations about the modelled agents conditioned only on the local observa","authors_text":"Filippos Christianos, Georgios Papoudakis, Stefano V. Albrecht","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T18:43:42Z","title":"Agent Modelling under Partial Observability for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09447","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":"sha256:23eb83edf41a682c933add62deb8372fc4ab8d3400f140ad9c911b8f6f5c1099","target":"record","created_at":"2026-07-05T03:30:06Z","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":"78f97abf04f9e39d61b76280514867b0514ff5522ef58d833cbcc4aed6e79c73","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T18:43:42Z","title_canon_sha256":"7506d8a9c436e0055c1c0b811f80a98be368e5b0e3488f31f5293ecdc29d3f49"},"schema_version":"1.0","source":{"id":"2006.09447","kind":"arxiv","version":4}},"canonical_sha256":"bfe771ea38043b6de12c4b2ecabe6836a515405b21074c29d5f60f9e35c45303","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfe771ea38043b6de12c4b2ecabe6836a515405b21074c29d5f60f9e35c45303","first_computed_at":"2026-07-05T03:30:06.396442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:30:06.396442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x+o6Jwj0sgXnuUvxrNniF8x5j+9txz76MXcU7yuDhjtgjC0E0TmyMSTPV53JL2Ppg8fjtOBzeAYN4laSkYURDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:30:06.396925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.09447","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23eb83edf41a682c933add62deb8372fc4ab8d3400f140ad9c911b8f6f5c1099","sha256:6808ed8aaff893317f67975583a3c31c0dbbe2d0ed28357d6328bf00935ab7cd"],"state_sha256":"8d62217c83e9937ff93dac47c12d6bc7897c9db2f184bfa219ab7acbbe351357"}