{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:A6R77LTWMSAAMISF5L2EAPIEWH","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":"c97ad0e1d14cac4d48c734f71d5ae3a4200ca9af90461c1f207221b54e01e198","cross_cats_sorted":["cs.GT","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-03-21T00:43:54Z","title_canon_sha256":"d6a596a0f691095ddc8a97b5f363906cc54680e1c0dad2fdc54715aaf49d5ac7"},"schema_version":"1.0","source":{"id":"2003.09540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.09540","created_at":"2026-07-05T02:37:55Z"},{"alias_kind":"arxiv_version","alias_value":"2003.09540v1","created_at":"2026-07-05T02:37:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.09540","created_at":"2026-07-05T02:37:55Z"},{"alias_kind":"pith_short_12","alias_value":"A6R77LTWMSAA","created_at":"2026-07-05T02:37:55Z"},{"alias_kind":"pith_short_16","alias_value":"A6R77LTWMSAAMISF","created_at":"2026-07-05T02:37:55Z"},{"alias_kind":"pith_short_8","alias_value":"A6R77LTW","created_at":"2026-07-05T02:37:55Z"}],"graph_snapshots":[{"event_id":"sha256:1b51bef829a75d695d505c045c43325cb5d477cdac7478b8c6fd57de567966c5","target":"graph","created_at":"2026-07-05T02:37:55Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2003.09540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alessandro Roncone, Bram Vanderborght, Christoffer Heckman, Guohui Ding, Joewie J. Koh, Kelly Merckaert, Lijun Chen, Marco M. Nicotra","cross_cats":["cs.GT","cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-03-21T00:43:54Z","title":"Distributed Reinforcement Learning for Cooperative Multi-Robot Object Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.09540","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":"sha256:80353f43254bc61abf3b77574abd85ed85898d035c722bab73b0714eab59d732","target":"record","created_at":"2026-07-05T02:37:55Z","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":"c97ad0e1d14cac4d48c734f71d5ae3a4200ca9af90461c1f207221b54e01e198","cross_cats_sorted":["cs.GT","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-03-21T00:43:54Z","title_canon_sha256":"d6a596a0f691095ddc8a97b5f363906cc54680e1c0dad2fdc54715aaf49d5ac7"},"schema_version":"1.0","source":{"id":"2003.09540","kind":"arxiv","version":1}},"canonical_sha256":"07a3ffae766480062245eaf4403d04b1d6df423ca07337474430a82ab7327f3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07a3ffae766480062245eaf4403d04b1d6df423ca07337474430a82ab7327f3e","first_computed_at":"2026-07-05T02:37:55.238138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:37:55.238138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F24ZMNyWEY59tJvQ++sfSTxgHrBfe2MEDP/eM5cyCQBrRYsH3JmDgA2vEIFnMrjxIQwNv2TmiOG5xysEA1QyDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:37:55.238527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.09540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80353f43254bc61abf3b77574abd85ed85898d035c722bab73b0714eab59d732","sha256:1b51bef829a75d695d505c045c43325cb5d477cdac7478b8c6fd57de567966c5"],"state_sha256":"2b6ad55abf14fc375953b9f2d2f42ebf04862a8275c7ff67d7358ae6c585d3ef"}