{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QKFYNDVKWJSXYKLWEVPOHX2R5X","short_pith_number":"pith:QKFYNDVK","canonical_record":{"source":{"id":"2110.12628","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-25T04:08:57Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"1fc3ebab81d5ee5a36291d20f693decf389a40530759a5f811fc9abaa3ab0e0c","abstract_canon_sha256":"874f87b06e6a72dfcbba5040dabacd204f054fb0158594ad3784f3839bb8196f"},"schema_version":"1.0"},"canonical_sha256":"828b868eaab2657c2976255ee3df51edca8ff00a66f15f9c3a8560f6cda6e309","source":{"kind":"arxiv","id":"2110.12628","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12628","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12628v1","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12628","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"pith_short_12","alias_value":"QKFYNDVKWJSX","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"pith_short_16","alias_value":"QKFYNDVKWJSXYKLW","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"pith_short_8","alias_value":"QKFYNDVK","created_at":"2026-07-05T03:26:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QKFYNDVKWJSXYKLWEVPOHX2R5X","target":"record","payload":{"canonical_record":{"source":{"id":"2110.12628","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-25T04:08:57Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"1fc3ebab81d5ee5a36291d20f693decf389a40530759a5f811fc9abaa3ab0e0c","abstract_canon_sha256":"874f87b06e6a72dfcbba5040dabacd204f054fb0158594ad3784f3839bb8196f"},"schema_version":"1.0"},"canonical_sha256":"828b868eaab2657c2976255ee3df51edca8ff00a66f15f9c3a8560f6cda6e309","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:21.529799Z","signature_b64":"aOSPT8UG6R44RzVa8DNN9TV2gpSxENFgzOOuDUda5yEDDzGv2PgJ49Y3KJFPSU4U+3TXtBg42neo9ifriB6VBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"828b868eaab2657c2976255ee3df51edca8ff00a66f15f9c3a8560f6cda6e309","last_reissued_at":"2026-07-05T03:26:21.529329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:21.529329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.12628","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":"2026-07-05T03:26:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+sJHGv8Kf6Cp7rL/kE1mdY8Pk/2NkJkEJeX1/Lt2hU4UhIacZjpejt/bAXDyVGhopZ5YIgd4qcJ7iJLbUwrBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:16:07.758411Z"},"content_sha256":"d19784e57ef73921bf69315ae4295ddbcb52b443812eb81787527b5c1bb38e19","schema_version":"1.0","event_id":"sha256:d19784e57ef73921bf69315ae4295ddbcb52b443812eb81787527b5c1bb38e19"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QKFYNDVKWJSXYKLWEVPOHX2R5X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recurrent Off-policy Baselines for Memory-based Continuous Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Hai Nguyen, Zhihan Yang","submitted_at":"2021-10-25T04:08:57Z","abstract_excerpt":"When the environment is partially observable (PO), a deep reinforcement learning (RL) agent must learn a suitable temporal representation of the entire history in addition to a strategy to control. This problem is not novel, and there have been model-free and model-based algorithms proposed for this problem. However, inspired by recent success in model-free image-based RL, we noticed the absence of a model-free baseline for history-based RL that (1) uses full history and (2) incorporates recent advances in off-policy continuous control. Therefore, we implement recurrent versions of DDPG, TD3, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12628","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.12628/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":"2026-07-05T03:26:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o9DgBaBzbsKt75e4Si72bd/rVzHNvGHo7eWxMjSR8HOP5ruS2uiwRqpJFN9EmmLn6lXN/OR8Of771/OCUkpFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:16:07.758784Z"},"content_sha256":"4a8e30077a22f4b9788c496670dab5d5f5f79a28f8743cf91380ec4f827adab3","schema_version":"1.0","event_id":"sha256:4a8e30077a22f4b9788c496670dab5d5f5f79a28f8743cf91380ec4f827adab3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X/bundle.json","state_url":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X/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":"2026-07-05T13:16:07Z","links":{"resolver":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X","bundle":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X/bundle.json","state":"https://pith.science/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QKFYNDVKWJSXYKLWEVPOHX2R5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QKFYNDVKWJSXYKLWEVPOHX2R5X","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":"874f87b06e6a72dfcbba5040dabacd204f054fb0158594ad3784f3839bb8196f","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-25T04:08:57Z","title_canon_sha256":"1fc3ebab81d5ee5a36291d20f693decf389a40530759a5f811fc9abaa3ab0e0c"},"schema_version":"1.0","source":{"id":"2110.12628","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12628","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12628v1","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12628","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"pith_short_12","alias_value":"QKFYNDVKWJSX","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"pith_short_16","alias_value":"QKFYNDVKWJSXYKLW","created_at":"2026-07-05T03:26:21Z"},{"alias_kind":"pith_short_8","alias_value":"QKFYNDVK","created_at":"2026-07-05T03:26:21Z"}],"graph_snapshots":[{"event_id":"sha256:4a8e30077a22f4b9788c496670dab5d5f5f79a28f8743cf91380ec4f827adab3","target":"graph","created_at":"2026-07-05T03:26:21Z","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/2110.12628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When the environment is partially observable (PO), a deep reinforcement learning (RL) agent must learn a suitable temporal representation of the entire history in addition to a strategy to control. This problem is not novel, and there have been model-free and model-based algorithms proposed for this problem. However, inspired by recent success in model-free image-based RL, we noticed the absence of a model-free baseline for history-based RL that (1) uses full history and (2) incorporates recent advances in off-policy continuous control. Therefore, we implement recurrent versions of DDPG, TD3, ","authors_text":"Hai Nguyen, Zhihan Yang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-25T04:08:57Z","title":"Recurrent Off-policy Baselines for Memory-based Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12628","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:d19784e57ef73921bf69315ae4295ddbcb52b443812eb81787527b5c1bb38e19","target":"record","created_at":"2026-07-05T03:26:21Z","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":"874f87b06e6a72dfcbba5040dabacd204f054fb0158594ad3784f3839bb8196f","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-25T04:08:57Z","title_canon_sha256":"1fc3ebab81d5ee5a36291d20f693decf389a40530759a5f811fc9abaa3ab0e0c"},"schema_version":"1.0","source":{"id":"2110.12628","kind":"arxiv","version":1}},"canonical_sha256":"828b868eaab2657c2976255ee3df51edca8ff00a66f15f9c3a8560f6cda6e309","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"828b868eaab2657c2976255ee3df51edca8ff00a66f15f9c3a8560f6cda6e309","first_computed_at":"2026-07-05T03:26:21.529329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:21.529329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aOSPT8UG6R44RzVa8DNN9TV2gpSxENFgzOOuDUda5yEDDzGv2PgJ49Y3KJFPSU4U+3TXtBg42neo9ifriB6VBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:21.529799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.12628","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d19784e57ef73921bf69315ae4295ddbcb52b443812eb81787527b5c1bb38e19","sha256:4a8e30077a22f4b9788c496670dab5d5f5f79a28f8743cf91380ec4f827adab3"],"state_sha256":"750beaca2f5cf9cab15a1e5caa5ab7c4486ff9fef29d9fb34f0b64ee6036dce0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5nom0KwN/NaYdZST7GYu3rhh+HucyUe5P+A21ORyCVLu7D/kh2Q3YaAwZK/Y8nZGT+kk18sj6sP+ASbVXHyRDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T13:16:07.760705Z","bundle_sha256":"f41328f8e363aa090c3adddbf3f643f52259d88ead952494df43d1ab1d15841a"}}