{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:KTBPE4WASLLY6MH5M3XQZ6YGHL","short_pith_number":"pith:KTBPE4WA","canonical_record":{"source":{"id":"1705.04862","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-13T17:39:54Z","cross_cats_sorted":[],"title_canon_sha256":"f8aadcb45a23ff90790805b53b690d00577269e4ca77d05caf7b579894054df0","abstract_canon_sha256":"4350d31bde7cc0bddf14b85f487d5b73158c6d6b613439500365f898b126b524"},"schema_version":"1.0"},"canonical_sha256":"54c2f272c092d78f30fd66ef0cfb063ade0aa2fbe280b6127bb02f0cd24406b1","source":{"kind":"arxiv","id":"1705.04862","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.04862","created_at":"2026-05-18T00:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"1705.04862v2","created_at":"2026-05-18T00:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04862","created_at":"2026-05-18T00:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"KTBPE4WASLLY","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"KTBPE4WASLLY6MH5","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"KTBPE4WA","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:KTBPE4WASLLY6MH5M3XQZ6YGHL","target":"record","payload":{"canonical_record":{"source":{"id":"1705.04862","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-13T17:39:54Z","cross_cats_sorted":[],"title_canon_sha256":"f8aadcb45a23ff90790805b53b690d00577269e4ca77d05caf7b579894054df0","abstract_canon_sha256":"4350d31bde7cc0bddf14b85f487d5b73158c6d6b613439500365f898b126b524"},"schema_version":"1.0"},"canonical_sha256":"54c2f272c092d78f30fd66ef0cfb063ade0aa2fbe280b6127bb02f0cd24406b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:22.881026Z","signature_b64":"1vyG8PbYTGjTcFVdHlX/+lX7rPOitABwzlm4uCOCE3syTuGmcDs8fyq8xtwgINFyL2FAOTRq/cHqbbHcJ4wNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54c2f272c092d78f30fd66ef0cfb063ade0aa2fbe280b6127bb02f0cd24406b1","last_reissued_at":"2026-05-18T00:44:22.880526Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:22.880526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.04862","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":"2026-05-18T00:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bARYwITlaxp2ahYBuqlkKBZHvIMRg+u2eMp/W/Bhtg6rVYGKC5cfa3SyxRTBsMvCw3B72t2MVHlrTUWL/9N+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T10:19:53.688510Z"},"content_sha256":"01ff3c1a46993c5ae01bd32092c7cfbc219fe0f4dd075cd3631670ca60049f08","schema_version":"1.0","event_id":"sha256:01ff3c1a46993c5ae01bd32092c7cfbc219fe0f4dd075cd3631670ca60049f08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:KTBPE4WASLLY6MH5M3XQZ6YGHL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Parallel Methods for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alfredo V. Clemente, Arjun Chandra, Humberto N. Castej\\'on","submitted_at":"2017-05-13T17:39:54Z","abstract_excerpt":"We propose a novel framework for efficient parallelization of deep reinforcement learning algorithms, enabling these algorithms to learn from multiple actors on a single machine. The framework is algorithm agnostic and can be applied to on-policy, off-policy, value based and policy gradient based algorithms. Given its inherent parallelism, the framework can be efficiently implemented on a GPU, allowing the usage of powerful models while significantly reducing training time. We demonstrate the effectiveness of our framework by implementing an advantage actor-critic algorithm on a GPU, using on-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04862","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":"2026-05-18T00:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lZFg9B4gcdn/u6pOzVz5gwLXGE8bvf3ixc3f7T7jQ+tWyE5zF2/N4Elsfl1ISc3wfzaB1co4Q+zgDgW1SAOtBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T10:19:53.688840Z"},"content_sha256":"a8d1c9c45c51048bd4e01f6851f28570cf743a0bef3a0e1cfdb773709f1fde11","schema_version":"1.0","event_id":"sha256:a8d1c9c45c51048bd4e01f6851f28570cf743a0bef3a0e1cfdb773709f1fde11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL/bundle.json","state_url":"https://pith.science/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL/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":"2026-06-09T10:19:53Z","links":{"resolver":"https://pith.science/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL","bundle":"https://pith.science/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL/bundle.json","state":"https://pith.science/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KTBPE4WASLLY6MH5M3XQZ6YGHL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:KTBPE4WASLLY6MH5M3XQZ6YGHL","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":"4350d31bde7cc0bddf14b85f487d5b73158c6d6b613439500365f898b126b524","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-13T17:39:54Z","title_canon_sha256":"f8aadcb45a23ff90790805b53b690d00577269e4ca77d05caf7b579894054df0"},"schema_version":"1.0","source":{"id":"1705.04862","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.04862","created_at":"2026-05-18T00:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"1705.04862v2","created_at":"2026-05-18T00:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04862","created_at":"2026-05-18T00:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"KTBPE4WASLLY","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"KTBPE4WASLLY6MH5","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"KTBPE4WA","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:a8d1c9c45c51048bd4e01f6851f28570cf743a0bef3a0e1cfdb773709f1fde11","target":"graph","created_at":"2026-05-18T00:44:22Z","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 novel framework for efficient parallelization of deep reinforcement learning algorithms, enabling these algorithms to learn from multiple actors on a single machine. The framework is algorithm agnostic and can be applied to on-policy, off-policy, value based and policy gradient based algorithms. Given its inherent parallelism, the framework can be efficiently implemented on a GPU, allowing the usage of powerful models while significantly reducing training time. We demonstrate the effectiveness of our framework by implementing an advantage actor-critic algorithm on a GPU, using on-","authors_text":"Alfredo V. Clemente, Arjun Chandra, Humberto N. Castej\\'on","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-13T17:39:54Z","title":"Efficient Parallel Methods for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04862","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":"sha256:01ff3c1a46993c5ae01bd32092c7cfbc219fe0f4dd075cd3631670ca60049f08","target":"record","created_at":"2026-05-18T00:44:22Z","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":"4350d31bde7cc0bddf14b85f487d5b73158c6d6b613439500365f898b126b524","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-13T17:39:54Z","title_canon_sha256":"f8aadcb45a23ff90790805b53b690d00577269e4ca77d05caf7b579894054df0"},"schema_version":"1.0","source":{"id":"1705.04862","kind":"arxiv","version":2}},"canonical_sha256":"54c2f272c092d78f30fd66ef0cfb063ade0aa2fbe280b6127bb02f0cd24406b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54c2f272c092d78f30fd66ef0cfb063ade0aa2fbe280b6127bb02f0cd24406b1","first_computed_at":"2026-05-18T00:44:22.880526Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:22.880526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1vyG8PbYTGjTcFVdHlX/+lX7rPOitABwzlm4uCOCE3syTuGmcDs8fyq8xtwgINFyL2FAOTRq/cHqbbHcJ4wNCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:22.881026Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.04862","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01ff3c1a46993c5ae01bd32092c7cfbc219fe0f4dd075cd3631670ca60049f08","sha256:a8d1c9c45c51048bd4e01f6851f28570cf743a0bef3a0e1cfdb773709f1fde11"],"state_sha256":"9434306c3271b25909045812cb2f37c50fd4c54ed73b36c488455f9a60c5dc17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jXEnr54rvVFyZ88hy7pMwDMRBA2EJp7xMQPxaSlwdqP1ZECBAB2EECocTN9L8ncUImSwb0KNJvxv+mEiDnUADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T10:19:53.690590Z","bundle_sha256":"9c1e7f575f0c48c1ad6a1a06e95778836a5a49c3632b8225e525174df9fe70e0"}}