{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5R4PDDC6Z7Y5NJ6DEDJD54E3AG","short_pith_number":"pith:5R4PDDC6","schema_version":"1.0","canonical_sha256":"ec78f18c5ecff1d6a7c320d23ef09b01b8ead9d01ab67a6f45a6f8c0b26e9688","source":{"kind":"arxiv","id":"2002.05189","version":1},"attestation_state":"computed","paper":{"title":"Intrinsic Motivation for Encouraging Synergistic Behavior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Gupta, Rohan Chitnis, Saurabh Gupta, Shubham Tulsiani","submitted_at":"2020-02-12T19:34:51Z","abstract_excerpt":"We study the role of intrinsic motivation as an exploration bias for reinforcement learning in sparse-reward synergistic tasks, which are tasks where multiple agents must work together to achieve a goal they could not individually. Our key idea is that a good guiding principle for intrinsic motivation in synergistic tasks is to take actions which affect the world in ways that would not be achieved if the agents were acting on their own. Thus, we propose to incentivize agents to take (joint) actions whose effects cannot be predicted via a composition of the predicted effect for each individual "},"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":"2002.05189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T19:34:51Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"66b0b60fedfeca7f49ea65b86ce54ba4b106b5df626e490ece558a3dcad94f5a","abstract_canon_sha256":"8728063285c003a48e5cf320bf2a050565ce7759b11fbaad1d6f36c85f6449aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:28.622507Z","signature_b64":"S24KZXxlrKpYEa9ydZOT3t3KKYhHwqtg8zFPhTjRziRqa3ckpJpzM/I+b0wdU0sB0kNS2ZcvO+x3apktWKJ0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec78f18c5ecff1d6a7c320d23ef09b01b8ead9d01ab67a6f45a6f8c0b26e9688","last_reissued_at":"2026-07-05T00:40:28.622025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:28.622025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intrinsic Motivation for Encouraging Synergistic Behavior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Gupta, Rohan Chitnis, Saurabh Gupta, Shubham Tulsiani","submitted_at":"2020-02-12T19:34:51Z","abstract_excerpt":"We study the role of intrinsic motivation as an exploration bias for reinforcement learning in sparse-reward synergistic tasks, which are tasks where multiple agents must work together to achieve a goal they could not individually. Our key idea is that a good guiding principle for intrinsic motivation in synergistic tasks is to take actions which affect the world in ways that would not be achieved if the agents were acting on their own. Thus, we propose to incentivize agents to take (joint) actions whose effects cannot be predicted via a composition of the predicted effect for each individual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05189","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/2002.05189/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":"2002.05189","created_at":"2026-07-05T00:40:28.622101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05189v1","created_at":"2026-07-05T00:40:28.622101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05189","created_at":"2026-07-05T00:40:28.622101+00:00"},{"alias_kind":"pith_short_12","alias_value":"5R4PDDC6Z7Y5","created_at":"2026-07-05T00:40:28.622101+00:00"},{"alias_kind":"pith_short_16","alias_value":"5R4PDDC6Z7Y5NJ6D","created_at":"2026-07-05T00:40:28.622101+00:00"},{"alias_kind":"pith_short_8","alias_value":"5R4PDDC6","created_at":"2026-07-05T00:40:28.622101+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/5R4PDDC6Z7Y5NJ6DEDJD54E3AG","json":"https://pith.science/pith/5R4PDDC6Z7Y5NJ6DEDJD54E3AG.json","graph_json":"https://pith.science/api/pith-number/5R4PDDC6Z7Y5NJ6DEDJD54E3AG/graph.json","events_json":"https://pith.science/api/pith-number/5R4PDDC6Z7Y5NJ6DEDJD54E3AG/events.json","paper":"https://pith.science/paper/5R4PDDC6"},"agent_actions":{"view_html":"https://pith.science/pith/5R4PDDC6Z7Y5NJ6DEDJD54E3AG","download_json":"https://pith.science/pith/5R4PDDC6Z7Y5NJ6DEDJD54E3AG.json","view_paper":"https://pith.science/paper/5R4PDDC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05189&json=true","fetch_graph":"https://pith.science/api/pith-number/5R4PDDC6Z7Y5NJ6DEDJD54E3AG/graph.json","fetch_events":"https://pith.science/api/pith-number/5R4PDDC6Z7Y5NJ6DEDJD54E3AG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5R4PDDC6Z7Y5NJ6DEDJD54E3AG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5R4PDDC6Z7Y5NJ6DEDJD54E3AG/action/storage_attestation","attest_author":"https://pith.science/pith/5R4PDDC6Z7Y5NJ6DEDJD54E3AG/action/author_attestation","sign_citation":"https://pith.science/pith/5R4PDDC6Z7Y5NJ6DEDJD54E3AG/action/citation_signature","submit_replication":"https://pith.science/pith/5R4PDDC6Z7Y5NJ6DEDJD54E3AG/action/replication_record"}},"created_at":"2026-07-05T00:40:28.622101+00:00","updated_at":"2026-07-05T00:40:28.622101+00:00"}