{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PYCENZYQW54V3SBQDQEFVD6A3V","short_pith_number":"pith:PYCENZYQ","canonical_record":{"source":{"id":"1903.00827","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-03T04:26:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b167abaffe6d8319c2fc2c6d1dbaeff6876d24327be4b16cf398ca3a1f5b24b4","abstract_canon_sha256":"e3f9e3efa69e5495f210636ea332a8e7785bc09bd954379bb4f719f7190e23bf"},"schema_version":"1.0"},"canonical_sha256":"7e0446e710b7795dc8301c085a8fc0dd4c8bb16c1c9c745ffd339f49d086ee54","source":{"kind":"arxiv","id":"1903.00827","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00827","created_at":"2026-05-17T23:52:13Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00827v1","created_at":"2026-05-17T23:52:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00827","created_at":"2026-05-17T23:52:13Z"},{"alias_kind":"pith_short_12","alias_value":"PYCENZYQW54V","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PYCENZYQW54V3SBQ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PYCENZYQ","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PYCENZYQW54V3SBQDQEFVD6A3V","target":"record","payload":{"canonical_record":{"source":{"id":"1903.00827","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-03T04:26:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b167abaffe6d8319c2fc2c6d1dbaeff6876d24327be4b16cf398ca3a1f5b24b4","abstract_canon_sha256":"e3f9e3efa69e5495f210636ea332a8e7785bc09bd954379bb4f719f7190e23bf"},"schema_version":"1.0"},"canonical_sha256":"7e0446e710b7795dc8301c085a8fc0dd4c8bb16c1c9c745ffd339f49d086ee54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:13.130913Z","signature_b64":"VVMD6GieQOheiRhNkaD3oW4jZ5ZdPfkrcZ2/ccrXmf5rB7gQJviSzQVim7SO3zwY1XeSCLKFM3C6QC7XcNiUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e0446e710b7795dc8301c085a8fc0dd4c8bb16c1c9c745ffd339f49d086ee54","last_reissued_at":"2026-05-17T23:52:13.130140Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:13.130140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.00827","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"afVyUPlIhfwr1XsUUYJ+/cx1bKR3uSn1jozlJhnM5I9g2CZP7/H+oq1SVoidVcFH9CSJI55d0K0dfRxVqZ8FCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:42:27.020810Z"},"content_sha256":"f6cd9a5a21dc70b88ec032730431682f468e958a5a3eead4379fc4d7aa6fb388","schema_version":"1.0","event_id":"sha256:f6cd9a5a21dc70b88ec032730431682f468e958a5a3eead4379fc4d7aa6fb388"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PYCENZYQW54V3SBQDQEFVD6A3V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Asynchronous Episodic Deep Deterministic Policy Gradient: Towards Continuous Control in Computationally Complex Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiale Chen, Weiping Li, Zhibo Chen, Zhizheng Zhang","submitted_at":"2019-03-03T04:26:32Z","abstract_excerpt":"Deep Deterministic Policy Gradient (DDPG) has been proved to be a successful reinforcement learning (RL) algorithm for continuous control tasks. However, DDPG still suffers from data insufficiency and training inefficiency, especially in computationally complex environments. In this paper, we propose Asynchronous Episodic DDPG (AE-DDPG), as an expansion of DDPG, which can achieve more effective learning with less training time required. First, we design a modified scheme for data collection in an asynchronous fashion. Generally, for asynchronous RL algorithms, sample efficiency or/and training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00827","kind":"arxiv","version":1},"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":"2026-05-17T23:52:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"arNdcZGLuQgC/V9zxIAqk0AdONn0EskBxfNpeUTuvB1banxlMkaGLbymNUO+h7I/4NCIh8QNLlJGv/VZDhA8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:42:27.021210Z"},"content_sha256":"4f093b393858d4374d46f7fe224fb665bd117f7ed81f0a1a5718e671bad17556","schema_version":"1.0","event_id":"sha256:4f093b393858d4374d46f7fe224fb665bd117f7ed81f0a1a5718e671bad17556"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYCENZYQW54V3SBQDQEFVD6A3V/bundle.json","state_url":"https://pith.science/pith/PYCENZYQW54V3SBQDQEFVD6A3V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYCENZYQW54V3SBQDQEFVD6A3V/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":"2026-05-31T06:42:27Z","links":{"resolver":"https://pith.science/pith/PYCENZYQW54V3SBQDQEFVD6A3V","bundle":"https://pith.science/pith/PYCENZYQW54V3SBQDQEFVD6A3V/bundle.json","state":"https://pith.science/pith/PYCENZYQW54V3SBQDQEFVD6A3V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYCENZYQW54V3SBQDQEFVD6A3V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PYCENZYQW54V3SBQDQEFVD6A3V","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":"e3f9e3efa69e5495f210636ea332a8e7785bc09bd954379bb4f719f7190e23bf","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-03T04:26:32Z","title_canon_sha256":"b167abaffe6d8319c2fc2c6d1dbaeff6876d24327be4b16cf398ca3a1f5b24b4"},"schema_version":"1.0","source":{"id":"1903.00827","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00827","created_at":"2026-05-17T23:52:13Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00827v1","created_at":"2026-05-17T23:52:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00827","created_at":"2026-05-17T23:52:13Z"},{"alias_kind":"pith_short_12","alias_value":"PYCENZYQW54V","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PYCENZYQW54V3SBQ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PYCENZYQ","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:4f093b393858d4374d46f7fe224fb665bd117f7ed81f0a1a5718e671bad17556","target":"graph","created_at":"2026-05-17T23:52:13Z","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":"Deep Deterministic Policy Gradient (DDPG) has been proved to be a successful reinforcement learning (RL) algorithm for continuous control tasks. However, DDPG still suffers from data insufficiency and training inefficiency, especially in computationally complex environments. In this paper, we propose Asynchronous Episodic DDPG (AE-DDPG), as an expansion of DDPG, which can achieve more effective learning with less training time required. First, we design a modified scheme for data collection in an asynchronous fashion. Generally, for asynchronous RL algorithms, sample efficiency or/and training","authors_text":"Jiale Chen, Weiping Li, Zhibo Chen, Zhizheng Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-03T04:26:32Z","title":"Asynchronous Episodic Deep Deterministic Policy Gradient: Towards Continuous Control in Computationally Complex Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00827","kind":"arxiv","version":1},"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:f6cd9a5a21dc70b88ec032730431682f468e958a5a3eead4379fc4d7aa6fb388","target":"record","created_at":"2026-05-17T23:52:13Z","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":"e3f9e3efa69e5495f210636ea332a8e7785bc09bd954379bb4f719f7190e23bf","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-03T04:26:32Z","title_canon_sha256":"b167abaffe6d8319c2fc2c6d1dbaeff6876d24327be4b16cf398ca3a1f5b24b4"},"schema_version":"1.0","source":{"id":"1903.00827","kind":"arxiv","version":1}},"canonical_sha256":"7e0446e710b7795dc8301c085a8fc0dd4c8bb16c1c9c745ffd339f49d086ee54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e0446e710b7795dc8301c085a8fc0dd4c8bb16c1c9c745ffd339f49d086ee54","first_computed_at":"2026-05-17T23:52:13.130140Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:13.130140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VVMD6GieQOheiRhNkaD3oW4jZ5ZdPfkrcZ2/ccrXmf5rB7gQJviSzQVim7SO3zwY1XeSCLKFM3C6QC7XcNiUBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:13.130913Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.00827","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6cd9a5a21dc70b88ec032730431682f468e958a5a3eead4379fc4d7aa6fb388","sha256:4f093b393858d4374d46f7fe224fb665bd117f7ed81f0a1a5718e671bad17556"],"state_sha256":"8c8342e48f64edc8c1a933c0d18bd9f5f3536aa160ca589c726c89296e6c7125"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w5QHhuwoRdRU18zfERVzJeU/2CmhB6awy0pDAEg/hmAnM4XJNKfEOjpcWQb+i7wX55S+AAyntKPyAIyPeyjLBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T06:42:27.023749Z","bundle_sha256":"91311a2cb43e550dee39961f5d379050ce99bab25b296af3d00cfc99b252d221"}}