{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:M35QEVRJ4BXQ3A5Y7BMVF4UABG","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":"f99894b3979f36d6934e777b32ead264fcd2ba041b0054bb3eec0860ad37af54","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T16:22:02Z","title_canon_sha256":"448bcf68fcfe4a2f600a2cee1ecb17fda1e65552b4b0c63fb8d6d5e07b0835c0"},"schema_version":"1.0","source":{"id":"1805.11016","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11016","created_at":"2026-05-18T00:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11016v2","created_at":"2026-05-18T00:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11016","created_at":"2026-05-18T00:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"M35QEVRJ4BXQ","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"M35QEVRJ4BXQ3A5Y","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"M35QEVRJ","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:f80038e0426bb6f14b059e873803b8a1aa3f92b363790427c74f080a998cec8e","target":"graph","created_at":"2026-05-18T00:14:28Z","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"},"paper":{"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.","authors_text":"Shagun Sodhani, Vardaan Pahuja","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T16:22:02Z","title":"Memory Augmented Self-Play"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11016","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:dc6497df0dacd0f6b5271a73a97dfa9843d4fb0f1bcc0b0ccbf1ec172984467a","target":"record","created_at":"2026-05-18T00:14:28Z","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":"f99894b3979f36d6934e777b32ead264fcd2ba041b0054bb3eec0860ad37af54","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T16:22:02Z","title_canon_sha256":"448bcf68fcfe4a2f600a2cee1ecb17fda1e65552b4b0c63fb8d6d5e07b0835c0"},"schema_version":"1.0","source":{"id":"1805.11016","kind":"arxiv","version":2}},"canonical_sha256":"66fb025629e06f0d83b8f85952f28009a69cef4beb7e56a45fe23883336cebe2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66fb025629e06f0d83b8f85952f28009a69cef4beb7e56a45fe23883336cebe2","first_computed_at":"2026-05-18T00:14:28.082179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:28.082179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ILI5y0553Nfx/dNQOlV5gSHelPc9//y1LEwrQ2uPFDPHCmjCBEApEcFEoB3SKYmwjpepwlLem7I7ZRoR6eo3AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:28.082883Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.11016","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc6497df0dacd0f6b5271a73a97dfa9843d4fb0f1bcc0b0ccbf1ec172984467a","sha256:f80038e0426bb6f14b059e873803b8a1aa3f92b363790427c74f080a998cec8e"],"state_sha256":"e69e52196e93442ff2d3dc53929aa76d4763123005ec1ff19f9fa3610fe4594d"}