{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DPGYOJ5L5B7PYV2YCZ6DBRWOYU","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":"aadbb67acb3dee01498c7fd809cf4a89c6e88f1cc55896d27084a2f8b0d6ce79","cross_cats_sorted":["cs.GT","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-15T18:10:46Z","title_canon_sha256":"d5871c93b46763f6284ae5f5e083ca8c6392e76dca4c98e4baba30afc3e71d7a"},"schema_version":"1.0","source":{"id":"2001.05458","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.05458","created_at":"2026-07-05T00:40:27Z"},{"alias_kind":"arxiv_version","alias_value":"2001.05458v2","created_at":"2026-07-05T00:40:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05458","created_at":"2026-07-05T00:40:27Z"},{"alias_kind":"pith_short_12","alias_value":"DPGYOJ5L5B7P","created_at":"2026-07-05T00:40:27Z"},{"alias_kind":"pith_short_16","alias_value":"DPGYOJ5L5B7PYV2Y","created_at":"2026-07-05T00:40:27Z"},{"alias_kind":"pith_short_8","alias_value":"DPGYOJ5L","created_at":"2026-07-05T00:40:27Z"}],"graph_snapshots":[{"event_id":"sha256:a7d4f9e83e999d99caa4b13391738d0ea7283ed0407332d38fb80b1d000ed8ad","target":"graph","created_at":"2026-07-05T00:40:27Z","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/2001.05458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In social dilemma situations, individual rationality leads to sub-optimal group outcomes. Several human engagements can be modeled as a sequential (multi-step) social dilemmas. However, in contrast to humans, Deep Reinforcement Learning agents trained to optimize individual rewards in sequential social dilemmas converge to selfish, mutually harmful behavior. We introduce a status-quo loss (SQLoss) that encourages an agent to stick to the status quo, rather than repeatedly changing its policy. We show how agents trained with SQLoss evolve cooperative behavior in several social dilemma matrix ga","authors_text":"Abhishek Sinha, Balaji Krishnamurthy, Jayakumar Subramanian, Mausoom Sarkar, Nikaash Puri, Pinkesh Badjatiya, Siddharth Singh","cross_cats":["cs.GT","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-15T18:10:46Z","title":"Inducing Cooperative behaviour in Sequential-Social dilemmas through Multi-Agent Reinforcement Learning using Status-Quo Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05458","kind":"arxiv","version":2},"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":"sha256:5b3905686f42f03e255d701a7e0f5c1cfddc2876db93d64655722a06e56d6168","target":"record","created_at":"2026-07-05T00:40:27Z","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":"aadbb67acb3dee01498c7fd809cf4a89c6e88f1cc55896d27084a2f8b0d6ce79","cross_cats_sorted":["cs.GT","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-15T18:10:46Z","title_canon_sha256":"d5871c93b46763f6284ae5f5e083ca8c6392e76dca4c98e4baba30afc3e71d7a"},"schema_version":"1.0","source":{"id":"2001.05458","kind":"arxiv","version":2}},"canonical_sha256":"1bcd8727abe87efc5758167c30c6cec50bbdb698ecfd24c83f7fb1029269a11b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bcd8727abe87efc5758167c30c6cec50bbdb698ecfd24c83f7fb1029269a11b","first_computed_at":"2026-07-05T00:40:27.566980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:27.566980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nDcxDp0Vzi4Ba1mmdUWdL9XfmGsZT9gfzgPEkh50ZPTrT97oVZUcklMAftkQycYQWytH4hOiFfvO+znuF0LOAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:27.567583Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.05458","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b3905686f42f03e255d701a7e0f5c1cfddc2876db93d64655722a06e56d6168","sha256:a7d4f9e83e999d99caa4b13391738d0ea7283ed0407332d38fb80b1d000ed8ad"],"state_sha256":"2532f29f5cdfaaac8a46aac1de51e5b8e2ddc2c6237537d5d2bebf9589de4674"}