{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:A6R77LTWMSAAMISF5L2EAPIEWH","short_pith_number":"pith:A6R77LTW","schema_version":"1.0","canonical_sha256":"07a3ffae766480062245eaf4403d04b1d6df423ca07337474430a82ab7327f3e","source":{"kind":"arxiv","id":"2003.09540","version":1},"attestation_state":"computed","paper":{"title":"Distributed Reinforcement Learning for Cooperative Multi-Robot Object Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","cs.MA"],"primary_cat":"cs.RO","authors_text":"Alessandro Roncone, Bram Vanderborght, Christoffer Heckman, Guohui Ding, Joewie J. Koh, Kelly Merckaert, Lijun Chen, Marco M. Nicotra","submitted_at":"2020-03-21T00:43:54Z","abstract_excerpt":"We consider solving a cooperative multi-robot object manipulation task using reinforcement learning (RL). We propose two distributed multi-agent RL approaches: distributed approximate RL (DA-RL), where each agent applies Q-learning with individual reward functions; and game-theoretic RL (GT-RL), where the agents update their Q-values based on the Nash equilibrium of a bimatrix Q-value game. We validate the proposed approaches in the setting of cooperative object manipulation with two simulated robot arms. Although we focus on a small system of two agents in this paper, both DA-RL and GT-RL app"},"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":"2003.09540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-03-21T00:43:54Z","cross_cats_sorted":["cs.GT","cs.LG","cs.MA"],"title_canon_sha256":"d6a596a0f691095ddc8a97b5f363906cc54680e1c0dad2fdc54715aaf49d5ac7","abstract_canon_sha256":"c97ad0e1d14cac4d48c734f71d5ae3a4200ca9af90461c1f207221b54e01e198"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:55.238527Z","signature_b64":"F24ZMNyWEY59tJvQ++sfSTxgHrBfe2MEDP/eM5cyCQBrRYsH3JmDgA2vEIFnMrjxIQwNv2TmiOG5xysEA1QyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07a3ffae766480062245eaf4403d04b1d6df423ca07337474430a82ab7327f3e","last_reissued_at":"2026-07-05T02:37:55.238138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:55.238138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Reinforcement Learning for Cooperative Multi-Robot Object Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG","cs.MA"],"primary_cat":"cs.RO","authors_text":"Alessandro Roncone, Bram Vanderborght, Christoffer Heckman, Guohui Ding, Joewie J. Koh, Kelly Merckaert, Lijun Chen, Marco M. Nicotra","submitted_at":"2020-03-21T00:43:54Z","abstract_excerpt":"We consider solving a cooperative multi-robot object manipulation task using reinforcement learning (RL). We propose two distributed multi-agent RL approaches: distributed approximate RL (DA-RL), where each agent applies Q-learning with individual reward functions; and game-theoretic RL (GT-RL), where the agents update their Q-values based on the Nash equilibrium of a bimatrix Q-value game. We validate the proposed approaches in the setting of cooperative object manipulation with two simulated robot arms. Although we focus on a small system of two agents in this paper, both DA-RL and GT-RL app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.09540","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/2003.09540/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":"2003.09540","created_at":"2026-07-05T02:37:55.238200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.09540v1","created_at":"2026-07-05T02:37:55.238200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.09540","created_at":"2026-07-05T02:37:55.238200+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6R77LTWMSAA","created_at":"2026-07-05T02:37:55.238200+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6R77LTWMSAAMISF","created_at":"2026-07-05T02:37:55.238200+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6R77LTW","created_at":"2026-07-05T02:37:55.238200+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/A6R77LTWMSAAMISF5L2EAPIEWH","json":"https://pith.science/pith/A6R77LTWMSAAMISF5L2EAPIEWH.json","graph_json":"https://pith.science/api/pith-number/A6R77LTWMSAAMISF5L2EAPIEWH/graph.json","events_json":"https://pith.science/api/pith-number/A6R77LTWMSAAMISF5L2EAPIEWH/events.json","paper":"https://pith.science/paper/A6R77LTW"},"agent_actions":{"view_html":"https://pith.science/pith/A6R77LTWMSAAMISF5L2EAPIEWH","download_json":"https://pith.science/pith/A6R77LTWMSAAMISF5L2EAPIEWH.json","view_paper":"https://pith.science/paper/A6R77LTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.09540&json=true","fetch_graph":"https://pith.science/api/pith-number/A6R77LTWMSAAMISF5L2EAPIEWH/graph.json","fetch_events":"https://pith.science/api/pith-number/A6R77LTWMSAAMISF5L2EAPIEWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6R77LTWMSAAMISF5L2EAPIEWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6R77LTWMSAAMISF5L2EAPIEWH/action/storage_attestation","attest_author":"https://pith.science/pith/A6R77LTWMSAAMISF5L2EAPIEWH/action/author_attestation","sign_citation":"https://pith.science/pith/A6R77LTWMSAAMISF5L2EAPIEWH/action/citation_signature","submit_replication":"https://pith.science/pith/A6R77LTWMSAAMISF5L2EAPIEWH/action/replication_record"}},"created_at":"2026-07-05T02:37:55.238200+00:00","updated_at":"2026-07-05T02:37:55.238200+00:00"}