{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IZ6FRUHFMEHIJBU2T5EWUBSGCT","short_pith_number":"pith:IZ6FRUHF","canonical_record":{"source":{"id":"1709.06011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2017-09-18T15:37:45Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","stat.ML"],"title_canon_sha256":"cf6b50dc624667f1b83319abf5b6e48da7aea5e538b14c058fb5ce5702d04d23","abstract_canon_sha256":"9d5bc62588fee647d9dff986b1f54270fbc009ce082fc5ae3e5c5b3cccd28528"},"schema_version":"1.0"},"canonical_sha256":"467c58d0e5610e84869a9f496a064614cc3f711450838c717953cde6c8a710e5","source":{"kind":"arxiv","id":"1709.06011","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06011","created_at":"2026-05-18T00:34:58Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06011v1","created_at":"2026-05-18T00:34:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06011","created_at":"2026-05-18T00:34:58Z"},{"alias_kind":"pith_short_12","alias_value":"IZ6FRUHFMEHI","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IZ6FRUHFMEHIJBU2","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IZ6FRUHF","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IZ6FRUHFMEHIJBU2T5EWUBSGCT","target":"record","payload":{"canonical_record":{"source":{"id":"1709.06011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2017-09-18T15:37:45Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","stat.ML"],"title_canon_sha256":"cf6b50dc624667f1b83319abf5b6e48da7aea5e538b14c058fb5ce5702d04d23","abstract_canon_sha256":"9d5bc62588fee647d9dff986b1f54270fbc009ce082fc5ae3e5c5b3cccd28528"},"schema_version":"1.0"},"canonical_sha256":"467c58d0e5610e84869a9f496a064614cc3f711450838c717953cde6c8a710e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:58.467932Z","signature_b64":"gcBDmv4AV8VvdvFO0MzqbhsuvdMunkcP7l65qLg2MrAMBZ2/Ljceil5ysYDoj6uQyq10TOf0OHuFQKdWhAepBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"467c58d0e5610e84869a9f496a064614cc3f711450838c717953cde6c8a710e5","last_reissued_at":"2026-05-18T00:34:58.467063Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:58.467063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.06011","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":"2026-05-18T00:34:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZCHytEpxGO98PuHb9itliCkqcl+pr3NNTIPD7UftIaa5a88YAJ/fxHLs2tJQ5L1zvX7yHdULFsPGzzdYZJp1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T10:33:34.518299Z"},"content_sha256":"ff45345e0451f1c1735fb9153ebcd2bc5f6f9fa178ae0f71d34e49b71025dedf","schema_version":"1.0","event_id":"sha256:ff45345e0451f1c1735fb9153ebcd2bc5f6f9fa178ae0f71d34e49b71025dedf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IZ6FRUHFMEHIJBU2T5EWUBSGCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Guided Deep Reinforcement Learning for Swarm Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","stat.ML"],"primary_cat":"cs.MA","authors_text":"Adrian \\v{S}o\\v{s}i\\'c, Gerhard Neumann, Maximilian H\\\"uttenrauch","submitted_at":"2017-09-18T15:37:45Z","abstract_excerpt":"In this paper, we investigate how to learn to control a group of cooperative agents with limited sensing capabilities such as robot swarms. The agents have only very basic sensor capabilities, yet in a group they can accomplish sophisticated tasks, such as distributed assembly or search and rescue tasks. Learning a policy for a group of agents is difficult due to distributed partial observability of the state. Here, we follow a guided approach where a critic has central access to the global state during learning, which simplifies the policy evaluation problem from a reinforcement learning poin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06011","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":"2026-05-18T00:34:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7qQSJSNKnPc7/7jLEXqXrNk3uQdjro+2mZBMIMVmp2nsddyWmh6gck7Qf3ZDFt8XuX/AGpzh4cVq/pSjTuQxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T10:33:34.518663Z"},"content_sha256":"9a9a39d6120b5a3e0ff702fcad6b49b134df21557bd8bb47a436783666469a74","schema_version":"1.0","event_id":"sha256:9a9a39d6120b5a3e0ff702fcad6b49b134df21557bd8bb47a436783666469a74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IZ6FRUHFMEHIJBU2T5EWUBSGCT/bundle.json","state_url":"https://pith.science/pith/IZ6FRUHFMEHIJBU2T5EWUBSGCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IZ6FRUHFMEHIJBU2T5EWUBSGCT/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":"2026-06-11T10:33:34Z","links":{"resolver":"https://pith.science/pith/IZ6FRUHFMEHIJBU2T5EWUBSGCT","bundle":"https://pith.science/pith/IZ6FRUHFMEHIJBU2T5EWUBSGCT/bundle.json","state":"https://pith.science/pith/IZ6FRUHFMEHIJBU2T5EWUBSGCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IZ6FRUHFMEHIJBU2T5EWUBSGCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IZ6FRUHFMEHIJBU2T5EWUBSGCT","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":"9d5bc62588fee647d9dff986b1f54270fbc009ce082fc5ae3e5c5b3cccd28528","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2017-09-18T15:37:45Z","title_canon_sha256":"cf6b50dc624667f1b83319abf5b6e48da7aea5e538b14c058fb5ce5702d04d23"},"schema_version":"1.0","source":{"id":"1709.06011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06011","created_at":"2026-05-18T00:34:58Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06011v1","created_at":"2026-05-18T00:34:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06011","created_at":"2026-05-18T00:34:58Z"},{"alias_kind":"pith_short_12","alias_value":"IZ6FRUHFMEHI","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IZ6FRUHFMEHIJBU2","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IZ6FRUHF","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:9a9a39d6120b5a3e0ff702fcad6b49b134df21557bd8bb47a436783666469a74","target":"graph","created_at":"2026-05-18T00:34:58Z","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":"In this paper, we investigate how to learn to control a group of cooperative agents with limited sensing capabilities such as robot swarms. The agents have only very basic sensor capabilities, yet in a group they can accomplish sophisticated tasks, such as distributed assembly or search and rescue tasks. Learning a policy for a group of agents is difficult due to distributed partial observability of the state. Here, we follow a guided approach where a critic has central access to the global state during learning, which simplifies the policy evaluation problem from a reinforcement learning poin","authors_text":"Adrian \\v{S}o\\v{s}i\\'c, Gerhard Neumann, Maximilian H\\\"uttenrauch","cross_cats":["cs.AI","cs.LG","cs.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2017-09-18T15:37:45Z","title":"Guided Deep Reinforcement Learning for Swarm Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06011","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:ff45345e0451f1c1735fb9153ebcd2bc5f6f9fa178ae0f71d34e49b71025dedf","target":"record","created_at":"2026-05-18T00:34:58Z","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":"9d5bc62588fee647d9dff986b1f54270fbc009ce082fc5ae3e5c5b3cccd28528","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2017-09-18T15:37:45Z","title_canon_sha256":"cf6b50dc624667f1b83319abf5b6e48da7aea5e538b14c058fb5ce5702d04d23"},"schema_version":"1.0","source":{"id":"1709.06011","kind":"arxiv","version":1}},"canonical_sha256":"467c58d0e5610e84869a9f496a064614cc3f711450838c717953cde6c8a710e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"467c58d0e5610e84869a9f496a064614cc3f711450838c717953cde6c8a710e5","first_computed_at":"2026-05-18T00:34:58.467063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:58.467063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gcBDmv4AV8VvdvFO0MzqbhsuvdMunkcP7l65qLg2MrAMBZ2/Ljceil5ysYDoj6uQyq10TOf0OHuFQKdWhAepBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:58.467932Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.06011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff45345e0451f1c1735fb9153ebcd2bc5f6f9fa178ae0f71d34e49b71025dedf","sha256:9a9a39d6120b5a3e0ff702fcad6b49b134df21557bd8bb47a436783666469a74"],"state_sha256":"5cbb0295b2226ca9268723b1090da6369795172669342e638f1826b66aaa40de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EBs1ltj5ztAZYjbDzrmXwy9B3CSg8jgWFar4MNxmjrGPMkS2XsDzdb+6WvdRVLCzInsMT5vlqDxzGn+Svcj8Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T10:33:34.520563Z","bundle_sha256":"09acc77b220300b91c71de03e884ec9335d959432c6d98a08217f9d009389554"}}