{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:M35QEVRJ4BXQ3A5Y7BMVF4UABG","short_pith_number":"pith:M35QEVRJ","schema_version":"1.0","canonical_sha256":"66fb025629e06f0d83b8f85952f28009a69cef4beb7e56a45fe23883336cebe2","source":{"kind":"arxiv","id":"1805.11016","version":2},"attestation_state":"computed","paper":{"title":"Memory Augmented Self-Play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Shagun Sodhani, Vardaan Pahuja","submitted_at":"2018-05-28T16:22:02Z","abstract_excerpt":"Self-play is an unsupervised training procedure which enables the reinforcement learning agents to explore the environment without requiring any external rewards. We augment the self-play setting by providing an external memory where the agent can store experience from the previous tasks. This enables the agent to come up with more diverse self-play tasks resulting in faster exploration of the environment. The agent pretrained in the memory augmented self-play setting easily outperforms the agent pretrained in no-memory self-play setting."},"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":"1805.11016","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T16:22:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"448bcf68fcfe4a2f600a2cee1ecb17fda1e65552b4b0c63fb8d6d5e07b0835c0","abstract_canon_sha256":"f99894b3979f36d6934e777b32ead264fcd2ba041b0054bb3eec0860ad37af54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:28.082883Z","signature_b64":"ILI5y0553Nfx/dNQOlV5gSHelPc9//y1LEwrQ2uPFDPHCmjCBEApEcFEoB3SKYmwjpepwlLem7I7ZRoR6eo3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66fb025629e06f0d83b8f85952f28009a69cef4beb7e56a45fe23883336cebe2","last_reissued_at":"2026-05-18T00:14:28.082179Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:28.082179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Augmented Self-Play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Shagun Sodhani, Vardaan Pahuja","submitted_at":"2018-05-28T16:22:02Z","abstract_excerpt":"Self-play is an unsupervised training procedure which enables the reinforcement learning agents to explore the environment without requiring any external rewards. We augment the self-play setting by providing an external memory where the agent can store experience from the previous tasks. This enables the agent to come up with more diverse self-play tasks resulting in faster exploration of the environment. The agent pretrained in the memory augmented self-play setting easily outperforms the agent pretrained in no-memory self-play setting."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11016","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":""},"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":"1805.11016","created_at":"2026-05-18T00:14:28.082295+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.11016v2","created_at":"2026-05-18T00:14:28.082295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11016","created_at":"2026-05-18T00:14:28.082295+00:00"},{"alias_kind":"pith_short_12","alias_value":"M35QEVRJ4BXQ","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"M35QEVRJ4BXQ3A5Y","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"M35QEVRJ","created_at":"2026-05-18T12:32:37.024351+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/M35QEVRJ4BXQ3A5Y7BMVF4UABG","json":"https://pith.science/pith/M35QEVRJ4BXQ3A5Y7BMVF4UABG.json","graph_json":"https://pith.science/api/pith-number/M35QEVRJ4BXQ3A5Y7BMVF4UABG/graph.json","events_json":"https://pith.science/api/pith-number/M35QEVRJ4BXQ3A5Y7BMVF4UABG/events.json","paper":"https://pith.science/paper/M35QEVRJ"},"agent_actions":{"view_html":"https://pith.science/pith/M35QEVRJ4BXQ3A5Y7BMVF4UABG","download_json":"https://pith.science/pith/M35QEVRJ4BXQ3A5Y7BMVF4UABG.json","view_paper":"https://pith.science/paper/M35QEVRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.11016&json=true","fetch_graph":"https://pith.science/api/pith-number/M35QEVRJ4BXQ3A5Y7BMVF4UABG/graph.json","fetch_events":"https://pith.science/api/pith-number/M35QEVRJ4BXQ3A5Y7BMVF4UABG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M35QEVRJ4BXQ3A5Y7BMVF4UABG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M35QEVRJ4BXQ3A5Y7BMVF4UABG/action/storage_attestation","attest_author":"https://pith.science/pith/M35QEVRJ4BXQ3A5Y7BMVF4UABG/action/author_attestation","sign_citation":"https://pith.science/pith/M35QEVRJ4BXQ3A5Y7BMVF4UABG/action/citation_signature","submit_replication":"https://pith.science/pith/M35QEVRJ4BXQ3A5Y7BMVF4UABG/action/replication_record"}},"created_at":"2026-05-18T00:14:28.082295+00:00","updated_at":"2026-05-18T00:14:28.082295+00:00"}