{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IEI3EM2WEWLW6KGCNUYWDZ3J6J","short_pith_number":"pith:IEI3EM2W","canonical_record":{"source":{"id":"1905.01357","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-04-19T04:22:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"50c8972aa39a9b37a687c09a754474429eb5a9c7b6f01911c958cb094f3ceafa","abstract_canon_sha256":"635897083ac31c33d010021e8754c205e7acf692553acdffe635fd2912041271"},"schema_version":"1.0"},"canonical_sha256":"4111b2335625976f28c26d3161e769f26ae84a0541a70166f28138f8f03366ac","source":{"kind":"arxiv","id":"1905.01357","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01357","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01357v2","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01357","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"IEI3EM2WEWLW","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IEI3EM2WEWLW6KGC","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IEI3EM2W","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IEI3EM2WEWLW6KGCNUYWDZ3J6J","target":"record","payload":{"canonical_record":{"source":{"id":"1905.01357","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-04-19T04:22:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"50c8972aa39a9b37a687c09a754474429eb5a9c7b6f01911c958cb094f3ceafa","abstract_canon_sha256":"635897083ac31c33d010021e8754c205e7acf692553acdffe635fd2912041271"},"schema_version":"1.0"},"canonical_sha256":"4111b2335625976f28c26d3161e769f26ae84a0541a70166f28138f8f03366ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:49.384949Z","signature_b64":"Cugf9Q45AF63gsXsN4GryvtuSWsNl5U3wiVyyWUf7DVp3Bq2YeNgN4wT4Nn0U8ttwjmZavKPRUWIyVWxvR3xDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4111b2335625976f28c26d3161e769f26ae84a0541a70166f28138f8f03366ac","last_reissued_at":"2026-05-17T23:44:49.384487Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:49.384487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.01357","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":"2026-05-17T23:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1YFV1RoQlf4pHXfY/6DYTaLs/WuoS2QG2XuhWi5XWv00VQ3tQ3K1QPVN7ZwUqEadNuNFqKBpH/U2ey7tgO3yBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:57:47.860672Z"},"content_sha256":"a5689da4354c3ceaf7507c8c51dbf0c893565f77ef57b1856e3963ee247926fb","schema_version":"1.0","event_id":"sha256:a5689da4354c3ceaf7507c8c51dbf0c893565f77ef57b1856e3963ee247926fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IEI3EM2WEWLW6KGCNUYWDZ3J6J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Teaching on a Budget in Multi-Agent Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Diego Perez-Liebana, Erc\\\"ument \\.Ilhan, Jeremy Gow","submitted_at":"2019-04-19T04:22:09Z","abstract_excerpt":"Deep Reinforcement Learning (RL) algorithms can solve complex sequential decision tasks successfully. However, they have a major drawback of having poor sample efficiency which can often be tackled by knowledge reuse. In Multi-Agent Reinforcement Learning (MARL) this drawback becomes worse, but at the same time, a new set of opportunities to leverage knowledge are also presented through agent interactions. One promising approach among these is peer-to-peer action advising through a teacher-student framework. Despite being introduced for single-agent RL originally, recent studies show that it c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01357","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":""},"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":"2026-05-17T23:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rnlBJgCr/c+yMnKK5/JQm0d2MXj1kNwCxm6BR+50X8DNjmzdj0/6/teebsTd88ZnEabS52/vRrcFaYjD4uv8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:57:47.861287Z"},"content_sha256":"0f619c3e1a8a574489afcf39162f1c71e4f61e146a4ebe3e4991a7380efff079","schema_version":"1.0","event_id":"sha256:0f619c3e1a8a574489afcf39162f1c71e4f61e146a4ebe3e4991a7380efff079"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEI3EM2WEWLW6KGCNUYWDZ3J6J/bundle.json","state_url":"https://pith.science/pith/IEI3EM2WEWLW6KGCNUYWDZ3J6J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEI3EM2WEWLW6KGCNUYWDZ3J6J/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":"2026-08-04T06:57:47Z","links":{"resolver":"https://pith.science/pith/IEI3EM2WEWLW6KGCNUYWDZ3J6J","bundle":"https://pith.science/pith/IEI3EM2WEWLW6KGCNUYWDZ3J6J/bundle.json","state":"https://pith.science/pith/IEI3EM2WEWLW6KGCNUYWDZ3J6J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEI3EM2WEWLW6KGCNUYWDZ3J6J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IEI3EM2WEWLW6KGCNUYWDZ3J6J","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":"635897083ac31c33d010021e8754c205e7acf692553acdffe635fd2912041271","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-04-19T04:22:09Z","title_canon_sha256":"50c8972aa39a9b37a687c09a754474429eb5a9c7b6f01911c958cb094f3ceafa"},"schema_version":"1.0","source":{"id":"1905.01357","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01357","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01357v2","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01357","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"IEI3EM2WEWLW","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IEI3EM2WEWLW6KGC","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IEI3EM2W","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:0f619c3e1a8a574489afcf39162f1c71e4f61e146a4ebe3e4991a7380efff079","target":"graph","created_at":"2026-05-17T23:44:49Z","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":"Deep Reinforcement Learning (RL) algorithms can solve complex sequential decision tasks successfully. However, they have a major drawback of having poor sample efficiency which can often be tackled by knowledge reuse. In Multi-Agent Reinforcement Learning (MARL) this drawback becomes worse, but at the same time, a new set of opportunities to leverage knowledge are also presented through agent interactions. One promising approach among these is peer-to-peer action advising through a teacher-student framework. Despite being introduced for single-agent RL originally, recent studies show that it c","authors_text":"Diego Perez-Liebana, Erc\\\"ument \\.Ilhan, Jeremy Gow","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-04-19T04:22:09Z","title":"Teaching on a Budget in Multi-Agent Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01357","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:a5689da4354c3ceaf7507c8c51dbf0c893565f77ef57b1856e3963ee247926fb","target":"record","created_at":"2026-05-17T23:44:49Z","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":"635897083ac31c33d010021e8754c205e7acf692553acdffe635fd2912041271","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-04-19T04:22:09Z","title_canon_sha256":"50c8972aa39a9b37a687c09a754474429eb5a9c7b6f01911c958cb094f3ceafa"},"schema_version":"1.0","source":{"id":"1905.01357","kind":"arxiv","version":2}},"canonical_sha256":"4111b2335625976f28c26d3161e769f26ae84a0541a70166f28138f8f03366ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4111b2335625976f28c26d3161e769f26ae84a0541a70166f28138f8f03366ac","first_computed_at":"2026-05-17T23:44:49.384487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:49.384487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cugf9Q45AF63gsXsN4GryvtuSWsNl5U3wiVyyWUf7DVp3Bq2YeNgN4wT4Nn0U8ttwjmZavKPRUWIyVWxvR3xDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:49.384949Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.01357","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5689da4354c3ceaf7507c8c51dbf0c893565f77ef57b1856e3963ee247926fb","sha256:0f619c3e1a8a574489afcf39162f1c71e4f61e146a4ebe3e4991a7380efff079"],"state_sha256":"42ef983d9cbc06ac7040418814c22380f3d0bc0d0be02ab0db1aaa7e9547a63c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/9ft6Yb2f+UNcLIcOntVReueXREwFsdZOZ0BqCp1I/iPMeIV6Xy2UcN4YUX5HoPbw6d2NFJhj9z7uwPzE5aWAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:57:47.866558Z","bundle_sha256":"97716aae9a5952b391fa63f6fb6ea63a3e20e35007e7f329428952e93c141482"}}