{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:W7I6TMHHC6FBLW4QM23L3SVRMU","short_pith_number":"pith:W7I6TMHH","schema_version":"1.0","canonical_sha256":"b7d1e9b0e7178a15db9066b6bdcab16511da97bb2f1e89ef6e01f7126d420349","source":{"kind":"arxiv","id":"2202.12174","version":1},"attestation_state":"computed","paper":{"title":"Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alain Andres, Esther Villar-Rodriguez, Javier Del Ser","submitted_at":"2022-02-24T16:15:51Z","abstract_excerpt":"In the early stages of human life, babies develop their skills by exploring different scenarios motivated by their inherent satisfaction rather than by extrinsic rewards from the environment. This behavior, referred to as intrinsic motivation, has emerged as one solution to address the exploration challenge derived from reinforcement learning environments with sparse rewards. Diverse exploration approaches have been proposed to accelerate the learning process over single- and multi-agent problems with homogeneous agents. However, scarce studies have elaborated on collaborative learning framewo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2202.12174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-24T16:15:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"72cc16ee635dab42b170100fa65299ed885feda2da86ec3376afb8f309824024","abstract_canon_sha256":"f3c57f66a43e3ddfd3623f30406db61a1b424ae1cc52759d71c6fd6c26577160"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:50.759413Z","signature_b64":"l8FEaFwHaxY3a9egE9xvlHfxE4/uhIgSWxu1YW4OKmpPcqJ4xr26JsFnFRtSlfUF2gEaMDkMAvJRmpECn3iGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7d1e9b0e7178a15db9066b6bdcab16511da97bb2f1e89ef6e01f7126d420349","last_reissued_at":"2026-07-05T03:59:50.758867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:50.758867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alain Andres, Esther Villar-Rodriguez, Javier Del Ser","submitted_at":"2022-02-24T16:15:51Z","abstract_excerpt":"In the early stages of human life, babies develop their skills by exploring different scenarios motivated by their inherent satisfaction rather than by extrinsic rewards from the environment. This behavior, referred to as intrinsic motivation, has emerged as one solution to address the exploration challenge derived from reinforcement learning environments with sparse rewards. Diverse exploration approaches have been proposed to accelerate the learning process over single- and multi-agent problems with homogeneous agents. However, scarce studies have elaborated on collaborative learning framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.12174","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/2202.12174/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2202.12174","created_at":"2026-07-05T03:59:50.758930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.12174v1","created_at":"2026-07-05T03:59:50.758930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.12174","created_at":"2026-07-05T03:59:50.758930+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7I6TMHHC6FB","created_at":"2026-07-05T03:59:50.758930+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7I6TMHHC6FBLW4Q","created_at":"2026-07-05T03:59:50.758930+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7I6TMHH","created_at":"2026-07-05T03:59:50.758930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W7I6TMHHC6FBLW4QM23L3SVRMU","json":"https://pith.science/pith/W7I6TMHHC6FBLW4QM23L3SVRMU.json","graph_json":"https://pith.science/api/pith-number/W7I6TMHHC6FBLW4QM23L3SVRMU/graph.json","events_json":"https://pith.science/api/pith-number/W7I6TMHHC6FBLW4QM23L3SVRMU/events.json","paper":"https://pith.science/paper/W7I6TMHH"},"agent_actions":{"view_html":"https://pith.science/pith/W7I6TMHHC6FBLW4QM23L3SVRMU","download_json":"https://pith.science/pith/W7I6TMHHC6FBLW4QM23L3SVRMU.json","view_paper":"https://pith.science/paper/W7I6TMHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.12174&json=true","fetch_graph":"https://pith.science/api/pith-number/W7I6TMHHC6FBLW4QM23L3SVRMU/graph.json","fetch_events":"https://pith.science/api/pith-number/W7I6TMHHC6FBLW4QM23L3SVRMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7I6TMHHC6FBLW4QM23L3SVRMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7I6TMHHC6FBLW4QM23L3SVRMU/action/storage_attestation","attest_author":"https://pith.science/pith/W7I6TMHHC6FBLW4QM23L3SVRMU/action/author_attestation","sign_citation":"https://pith.science/pith/W7I6TMHHC6FBLW4QM23L3SVRMU/action/citation_signature","submit_replication":"https://pith.science/pith/W7I6TMHHC6FBLW4QM23L3SVRMU/action/replication_record"}},"created_at":"2026-07-05T03:59:50.758930+00:00","updated_at":"2026-07-05T03:59:50.758930+00:00"}