{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WRSP2PPD5JME5XAFPYMXOATJYL","short_pith_number":"pith:WRSP2PPD","schema_version":"1.0","canonical_sha256":"b464fd3de3ea584edc057e19770269c2fa8d59d457e10d6deb04e8d5686c77c3","source":{"kind":"arxiv","id":"2107.08295","version":2},"attestation_state":"computed","paper":{"title":"Communicating via Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Christian Schroeder de Witt, Jakob Foerster, J. Zico Kolter, Luisa Zintgraf, Martin Strohmeier, Maximilian Igl, Philip Torr, Samuel Sokota, Shimon Whiteson","submitted_at":"2021-07-17T17:44:30Z","abstract_excerpt":"We consider the problem of communicating exogenous information by means of Markov decision process trajectories. This setting, which we call a Markov coding game (MCG), generalizes both source coding and a large class of referential games. MCGs also isolate a problem that is important in decentralized control settings in which cheap-talk is not available -- namely, they require balancing communication with the associated cost of communicating. We contribute a theoretically grounded approach to MCGs based on maximum entropy reinforcement learning and minimum entropy coupling that we call MEME. "},"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":"2107.08295","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-07-17T17:44:30Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"c6a419b0062de00330d53d7aafe9ecf90574cb61cd3e8a5d4278342aa7d56382","abstract_canon_sha256":"45c1b197369b85b76b7f951428b39eb34517bc823929aa0ec6e2712d3d02c1a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:51.903529Z","signature_b64":"er+6hRxsxoAbkhMZYwzwMmYhNIrTyG8BwSg7acdVXVeA+Rk0vbckpcMITm7xDYtY6fFks2SpsPanljOYbaI1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b464fd3de3ea584edc057e19770269c2fa8d59d457e10d6deb04e8d5686c77c3","last_reissued_at":"2026-07-05T04:30:51.903160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:51.903160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Communicating via Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Christian Schroeder de Witt, Jakob Foerster, J. Zico Kolter, Luisa Zintgraf, Martin Strohmeier, Maximilian Igl, Philip Torr, Samuel Sokota, Shimon Whiteson","submitted_at":"2021-07-17T17:44:30Z","abstract_excerpt":"We consider the problem of communicating exogenous information by means of Markov decision process trajectories. This setting, which we call a Markov coding game (MCG), generalizes both source coding and a large class of referential games. MCGs also isolate a problem that is important in decentralized control settings in which cheap-talk is not available -- namely, they require balancing communication with the associated cost of communicating. We contribute a theoretically grounded approach to MCGs based on maximum entropy reinforcement learning and minimum entropy coupling that we call MEME. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08295","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.08295/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":"2107.08295","created_at":"2026-07-05T04:30:51.903212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.08295v2","created_at":"2026-07-05T04:30:51.903212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08295","created_at":"2026-07-05T04:30:51.903212+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRSP2PPD5JME","created_at":"2026-07-05T04:30:51.903212+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRSP2PPD5JME5XAF","created_at":"2026-07-05T04:30:51.903212+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRSP2PPD","created_at":"2026-07-05T04:30:51.903212+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/WRSP2PPD5JME5XAFPYMXOATJYL","json":"https://pith.science/pith/WRSP2PPD5JME5XAFPYMXOATJYL.json","graph_json":"https://pith.science/api/pith-number/WRSP2PPD5JME5XAFPYMXOATJYL/graph.json","events_json":"https://pith.science/api/pith-number/WRSP2PPD5JME5XAFPYMXOATJYL/events.json","paper":"https://pith.science/paper/WRSP2PPD"},"agent_actions":{"view_html":"https://pith.science/pith/WRSP2PPD5JME5XAFPYMXOATJYL","download_json":"https://pith.science/pith/WRSP2PPD5JME5XAFPYMXOATJYL.json","view_paper":"https://pith.science/paper/WRSP2PPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.08295&json=true","fetch_graph":"https://pith.science/api/pith-number/WRSP2PPD5JME5XAFPYMXOATJYL/graph.json","fetch_events":"https://pith.science/api/pith-number/WRSP2PPD5JME5XAFPYMXOATJYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRSP2PPD5JME5XAFPYMXOATJYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRSP2PPD5JME5XAFPYMXOATJYL/action/storage_attestation","attest_author":"https://pith.science/pith/WRSP2PPD5JME5XAFPYMXOATJYL/action/author_attestation","sign_citation":"https://pith.science/pith/WRSP2PPD5JME5XAFPYMXOATJYL/action/citation_signature","submit_replication":"https://pith.science/pith/WRSP2PPD5JME5XAFPYMXOATJYL/action/replication_record"}},"created_at":"2026-07-05T04:30:51.903212+00:00","updated_at":"2026-07-05T04:30:51.903212+00:00"}