{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:77M3W4GBAK6KW4BUWTTSSHI7U2","short_pith_number":"pith:77M3W4GB","canonical_record":{"source":{"id":"1602.01783","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-04T18:38:41Z","cross_cats_sorted":[],"title_canon_sha256":"991fe6f4bc1975bac9f95081205828ba86a141492c744055b5c736692005cd08","abstract_canon_sha256":"5d94b75a1fdb5ada50f9ede6ff6d4f52b3854c5de09c36540ba51ddf13788c29"},"schema_version":"1.0"},"canonical_sha256":"ffd9bb70c102bcab7034b4e7291d1fa693a43b664fb77608b5e13cc07ad9a9b8","source":{"kind":"arxiv","id":"1602.01783","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.01783","created_at":"2026-05-18T01:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"1602.01783v2","created_at":"2026-05-18T01:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.01783","created_at":"2026-05-18T01:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"77M3W4GBAK6K","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"77M3W4GBAK6KW4BU","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"77M3W4GB","created_at":"2026-05-18T12:30:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:77M3W4GBAK6KW4BUWTTSSHI7U2","target":"record","payload":{"canonical_record":{"source":{"id":"1602.01783","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-04T18:38:41Z","cross_cats_sorted":[],"title_canon_sha256":"991fe6f4bc1975bac9f95081205828ba86a141492c744055b5c736692005cd08","abstract_canon_sha256":"5d94b75a1fdb5ada50f9ede6ff6d4f52b3854c5de09c36540ba51ddf13788c29"},"schema_version":"1.0"},"canonical_sha256":"ffd9bb70c102bcab7034b4e7291d1fa693a43b664fb77608b5e13cc07ad9a9b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:22.591894Z","signature_b64":"HDcPWF8crDNx8TYWRWfAlaRLvZFNxAmUxLnVSsPIQvlIgxKU2gWzrnyL92qKQGuRDP2uaBR518JtL/jSQqYTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffd9bb70c102bcab7034b4e7291d1fa693a43b664fb77608b5e13cc07ad9a9b8","last_reissued_at":"2026-05-18T01:12:22.591566Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:22.591566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.01783","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nTvLuqD935P8w+UQypl8cJpeJ0ef/qS8K5DlXjboYBSEOCRX8ebBA1q2oah4QaH0J0jgeP1/oHmuGK7MI3i2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T13:32:42.943107Z"},"content_sha256":"125fcc7f45ac203350cad70eced680bbfee63d2bea26a06f34e3532af0439d70","schema_version":"1.0","event_id":"sha256:125fcc7f45ac203350cad70eced680bbfee63d2bea26a06f34e3532af0439d70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:77M3W4GBAK6KW4BUWTTSSHI7U2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Asynchronous Methods for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adri\\`a Puigdom\\`enech Badia, Alex Graves, David Silver, Koray Kavukcuoglu, Mehdi Mirza, Tim Harley, Timothy P. Lillicrap, Volodymyr Mnih","submitted_at":"2016-02-04T18:38:41Z","abstract_excerpt":"We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard reinforcement learning algorithms and show that parallel actor-learners have a stabilizing effect on training allowing all four methods to successfully train neural network controllers. The best performing method, an asynchronous variant of actor-critic, surpasses the current state-of-the-art on the Atari domain while training for half the time on a single multi-c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.01783","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WQIU+5BKh82QLZiTrn4sDJoSaZLz6O8g+Ro2+q4j1C7WV+Aq98LbSGPx6Z0ZlcomvsIB340XmKdWoUFc5758DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T13:32:42.943467Z"},"content_sha256":"5d634ed2ed5f0f51db76108e18abbea66f1914ba63065d2c6e307126d72eef85","schema_version":"1.0","event_id":"sha256:5d634ed2ed5f0f51db76108e18abbea66f1914ba63065d2c6e307126d72eef85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77M3W4GBAK6KW4BUWTTSSHI7U2/bundle.json","state_url":"https://pith.science/pith/77M3W4GBAK6KW4BUWTTSSHI7U2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77M3W4GBAK6KW4BUWTTSSHI7U2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-22T13:32:42Z","links":{"resolver":"https://pith.science/pith/77M3W4GBAK6KW4BUWTTSSHI7U2","bundle":"https://pith.science/pith/77M3W4GBAK6KW4BUWTTSSHI7U2/bundle.json","state":"https://pith.science/pith/77M3W4GBAK6KW4BUWTTSSHI7U2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77M3W4GBAK6KW4BUWTTSSHI7U2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:77M3W4GBAK6KW4BUWTTSSHI7U2","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":"5d94b75a1fdb5ada50f9ede6ff6d4f52b3854c5de09c36540ba51ddf13788c29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-04T18:38:41Z","title_canon_sha256":"991fe6f4bc1975bac9f95081205828ba86a141492c744055b5c736692005cd08"},"schema_version":"1.0","source":{"id":"1602.01783","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.01783","created_at":"2026-05-18T01:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"1602.01783v2","created_at":"2026-05-18T01:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.01783","created_at":"2026-05-18T01:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"77M3W4GBAK6K","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"77M3W4GBAK6KW4BU","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"77M3W4GB","created_at":"2026-05-18T12:30:04Z"}],"graph_snapshots":[{"event_id":"sha256:5d634ed2ed5f0f51db76108e18abbea66f1914ba63065d2c6e307126d72eef85","target":"graph","created_at":"2026-05-18T01:12:22Z","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":"We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard reinforcement learning algorithms and show that parallel actor-learners have a stabilizing effect on training allowing all four methods to successfully train neural network controllers. The best performing method, an asynchronous variant of actor-critic, surpasses the current state-of-the-art on the Atari domain while training for half the time on a single multi-c","authors_text":"Adri\\`a Puigdom\\`enech Badia, Alex Graves, David Silver, Koray Kavukcuoglu, Mehdi Mirza, Tim Harley, Timothy P. Lillicrap, Volodymyr Mnih","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-04T18:38:41Z","title":"Asynchronous Methods for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.01783","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":"sha256:125fcc7f45ac203350cad70eced680bbfee63d2bea26a06f34e3532af0439d70","target":"record","created_at":"2026-05-18T01:12:22Z","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":"5d94b75a1fdb5ada50f9ede6ff6d4f52b3854c5de09c36540ba51ddf13788c29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-04T18:38:41Z","title_canon_sha256":"991fe6f4bc1975bac9f95081205828ba86a141492c744055b5c736692005cd08"},"schema_version":"1.0","source":{"id":"1602.01783","kind":"arxiv","version":2}},"canonical_sha256":"ffd9bb70c102bcab7034b4e7291d1fa693a43b664fb77608b5e13cc07ad9a9b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffd9bb70c102bcab7034b4e7291d1fa693a43b664fb77608b5e13cc07ad9a9b8","first_computed_at":"2026-05-18T01:12:22.591566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:22.591566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HDcPWF8crDNx8TYWRWfAlaRLvZFNxAmUxLnVSsPIQvlIgxKU2gWzrnyL92qKQGuRDP2uaBR518JtL/jSQqYTBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:22.591894Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.01783","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:125fcc7f45ac203350cad70eced680bbfee63d2bea26a06f34e3532af0439d70","sha256:5d634ed2ed5f0f51db76108e18abbea66f1914ba63065d2c6e307126d72eef85"],"state_sha256":"fa33c3f0c86dfc8a88e92e6f8d080b8dc1b35f0f63e1a12283e7c4b123de5c17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DDFUAJSjRQMqpcUM24Md6643vV+r8zHzRL8JQ8pWAYUPTrFlUQBxYZvjexg/HnsE2frty9Es8frXWiZkL+muDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T13:32:42.946044Z","bundle_sha256":"15a8a6315bd4e4452fdbb23a09b2673d3df96395c501bdd7975f987b75b9b9c8"}}