{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:SWNLBAQ7CWOICQSY7CIHWWQHA6","short_pith_number":"pith:SWNLBAQ7","canonical_record":{"source":{"id":"2109.10552","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-22T07:30:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6c2beb1743e4dfa809d960686fef79db6ca93dc76c98495592b1846398feafe","abstract_canon_sha256":"5bfe7cd6069d7b8a11a2ffeabd49d9d6119cd81aaa010bc10cb7ffb46b9178e4"},"schema_version":"1.0"},"canonical_sha256":"959ab0821f159c814258f8907b5a0707b1fdfa676f1b5cb0ed33c3b8f53ff5c8","source":{"kind":"arxiv","id":"2109.10552","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.10552","created_at":"2026-07-05T04:38:44Z"},{"alias_kind":"arxiv_version","alias_value":"2109.10552v2","created_at":"2026-07-05T04:38:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10552","created_at":"2026-07-05T04:38:44Z"},{"alias_kind":"pith_short_12","alias_value":"SWNLBAQ7CWOI","created_at":"2026-07-05T04:38:44Z"},{"alias_kind":"pith_short_16","alias_value":"SWNLBAQ7CWOICQSY","created_at":"2026-07-05T04:38:44Z"},{"alias_kind":"pith_short_8","alias_value":"SWNLBAQ7","created_at":"2026-07-05T04:38:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:SWNLBAQ7CWOICQSY7CIHWWQHA6","target":"record","payload":{"canonical_record":{"source":{"id":"2109.10552","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-22T07:30:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6c2beb1743e4dfa809d960686fef79db6ca93dc76c98495592b1846398feafe","abstract_canon_sha256":"5bfe7cd6069d7b8a11a2ffeabd49d9d6119cd81aaa010bc10cb7ffb46b9178e4"},"schema_version":"1.0"},"canonical_sha256":"959ab0821f159c814258f8907b5a0707b1fdfa676f1b5cb0ed33c3b8f53ff5c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:44.842707Z","signature_b64":"4UsyQWtazQ4xsGDNgVyFnsYWjNews8FY2SWpajpQYPO1RbOYl/qAwCfrt/LrI3BBlsz3MUOXFawkCL4YY/wUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"959ab0821f159c814258f8907b5a0707b1fdfa676f1b5cb0ed33c3b8f53ff5c8","last_reissued_at":"2026-07-05T04:38:44.842273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:44.842273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.10552","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":"2026-07-05T04:38:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H60R3O1dH+fgMd4hOq7/qPsji/KUUl41177vgk6itbvSjmqTnGEQzodIOFy3lTr9C/78lhFL0MjJnlBVSaQJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:07:23.465040Z"},"content_sha256":"fc6798158d0ba56f6cf246d35b1ce162474e5d3738bd9012ef511aabb4d26587","schema_version":"1.0","event_id":"sha256:fc6798158d0ba56f6cf246d35b1ce162474e5d3738bd9012ef511aabb4d26587"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:SWNLBAQ7CWOICQSY7CIHWWQHA6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chen Gong, Huangyuan Su, Qiang He, Xinwen Hou","submitted_at":"2021-09-22T07:30:52Z","abstract_excerpt":"During the training of a reinforcement learning (RL) agent, the distribution of training data is non-stationary as the agent's behavior changes over time. Therefore, there is a risk that the agent is overspecialized to a particular distribution and its performance suffers in the larger picture. Ensemble RL can mitigate this issue by learning a robust policy. However, it suffers from heavy computational resource consumption due to the newly introduced value and policy functions. In this paper, to avoid the notorious resources consumption issue, we design a novel and simple ensemble deep RL fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10552","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.10552/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:38:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pd/K5KItaoXQOi5sneVc6LupQ4H8XnnUpE59ynQ9YKS5GJsEX+92RBfc8MqEin5FoHunl67L3eVk9JEwQbIcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:07:23.465551Z"},"content_sha256":"0227090b4a5b35e0612700d17f238527c8280d4ab0fe5fe34ae7d15e3d81240f","schema_version":"1.0","event_id":"sha256:0227090b4a5b35e0612700d17f238527c8280d4ab0fe5fe34ae7d15e3d81240f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SWNLBAQ7CWOICQSY7CIHWWQHA6/bundle.json","state_url":"https://pith.science/pith/SWNLBAQ7CWOICQSY7CIHWWQHA6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SWNLBAQ7CWOICQSY7CIHWWQHA6/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":"2026-08-04T09:07:23Z","links":{"resolver":"https://pith.science/pith/SWNLBAQ7CWOICQSY7CIHWWQHA6","bundle":"https://pith.science/pith/SWNLBAQ7CWOICQSY7CIHWWQHA6/bundle.json","state":"https://pith.science/pith/SWNLBAQ7CWOICQSY7CIHWWQHA6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SWNLBAQ7CWOICQSY7CIHWWQHA6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SWNLBAQ7CWOICQSY7CIHWWQHA6","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":"5bfe7cd6069d7b8a11a2ffeabd49d9d6119cd81aaa010bc10cb7ffb46b9178e4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-22T07:30:52Z","title_canon_sha256":"d6c2beb1743e4dfa809d960686fef79db6ca93dc76c98495592b1846398feafe"},"schema_version":"1.0","source":{"id":"2109.10552","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.10552","created_at":"2026-07-05T04:38:44Z"},{"alias_kind":"arxiv_version","alias_value":"2109.10552v2","created_at":"2026-07-05T04:38:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10552","created_at":"2026-07-05T04:38:44Z"},{"alias_kind":"pith_short_12","alias_value":"SWNLBAQ7CWOI","created_at":"2026-07-05T04:38:44Z"},{"alias_kind":"pith_short_16","alias_value":"SWNLBAQ7CWOICQSY","created_at":"2026-07-05T04:38:44Z"},{"alias_kind":"pith_short_8","alias_value":"SWNLBAQ7","created_at":"2026-07-05T04:38:44Z"}],"graph_snapshots":[{"event_id":"sha256:0227090b4a5b35e0612700d17f238527c8280d4ab0fe5fe34ae7d15e3d81240f","target":"graph","created_at":"2026-07-05T04:38:44Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.10552/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"During the training of a reinforcement learning (RL) agent, the distribution of training data is non-stationary as the agent's behavior changes over time. Therefore, there is a risk that the agent is overspecialized to a particular distribution and its performance suffers in the larger picture. Ensemble RL can mitigate this issue by learning a robust policy. However, it suffers from heavy computational resource consumption due to the newly introduced value and policy functions. In this paper, to avoid the notorious resources consumption issue, we design a novel and simple ensemble deep RL fram","authors_text":"Chen Gong, Huangyuan Su, Qiang He, Xinwen Hou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-22T07:30:52Z","title":"MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10552","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:fc6798158d0ba56f6cf246d35b1ce162474e5d3738bd9012ef511aabb4d26587","target":"record","created_at":"2026-07-05T04:38:44Z","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":"5bfe7cd6069d7b8a11a2ffeabd49d9d6119cd81aaa010bc10cb7ffb46b9178e4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-22T07:30:52Z","title_canon_sha256":"d6c2beb1743e4dfa809d960686fef79db6ca93dc76c98495592b1846398feafe"},"schema_version":"1.0","source":{"id":"2109.10552","kind":"arxiv","version":2}},"canonical_sha256":"959ab0821f159c814258f8907b5a0707b1fdfa676f1b5cb0ed33c3b8f53ff5c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"959ab0821f159c814258f8907b5a0707b1fdfa676f1b5cb0ed33c3b8f53ff5c8","first_computed_at":"2026-07-05T04:38:44.842273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:38:44.842273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4UsyQWtazQ4xsGDNgVyFnsYWjNews8FY2SWpajpQYPO1RbOYl/qAwCfrt/LrI3BBlsz3MUOXFawkCL4YY/wUCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:38:44.842707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.10552","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc6798158d0ba56f6cf246d35b1ce162474e5d3738bd9012ef511aabb4d26587","sha256:0227090b4a5b35e0612700d17f238527c8280d4ab0fe5fe34ae7d15e3d81240f"],"state_sha256":"1a5c87b5f1004a4e23c8015997984839b4b8a8a28aae8f6dee7c6ea3c543d39b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RM387t8rA16brBtV3Jd/PMcQNtKv8S0zUpHEBUCQtD4qwnLbuBDsn+lQ3q71JqOBuKDB1vhyF6ql91WSE8boCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:07:23.470406Z","bundle_sha256":"b011549c9c05bdac80584583518e7d6fc64a9188cc72881594039f75d96fc672"}}