{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:5B4I4DYOKYNJUJSLKCEQGEHSTA","short_pith_number":"pith:5B4I4DYO","canonical_record":{"source":{"id":"2006.15199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-26T20:21:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7c71eb4d92b2e00d630b448b67fb2baec8e42d13bcf215b122b032bdd1f83739","abstract_canon_sha256":"ec081b6d2ebdab1463c23b58a389ae6f0ae8488906e34cae14b75725c878f60e"},"schema_version":"1.0"},"canonical_sha256":"e8788e0f0e561a9a264b50890310f2982aad45168fa29ff8924ecc23a4a51b3d","source":{"kind":"arxiv","id":"2006.15199","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.15199","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"arxiv_version","alias_value":"2006.15199v1","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15199","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"pith_short_12","alias_value":"5B4I4DYOKYNJ","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"pith_short_16","alias_value":"5B4I4DYOKYNJUJSL","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"pith_short_8","alias_value":"5B4I4DYO","created_at":"2026-07-05T01:14:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:5B4I4DYOKYNJUJSLKCEQGEHSTA","target":"record","payload":{"canonical_record":{"source":{"id":"2006.15199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-26T20:21:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7c71eb4d92b2e00d630b448b67fb2baec8e42d13bcf215b122b032bdd1f83739","abstract_canon_sha256":"ec081b6d2ebdab1463c23b58a389ae6f0ae8488906e34cae14b75725c878f60e"},"schema_version":"1.0"},"canonical_sha256":"e8788e0f0e561a9a264b50890310f2982aad45168fa29ff8924ecc23a4a51b3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:14:03.070462Z","signature_b64":"4Xj/a1DJ2QgAn3x182IikQEJKihKEJBf5n4U/RxmcLzu4YWWlnWY1MbnXAaxJELv9BSWZwK4NBZczOUk6Y/eDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8788e0f0e561a9a264b50890310f2982aad45168fa29ff8924ecc23a4a51b3d","last_reissued_at":"2026-07-05T01:14:03.070039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:14:03.070039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.15199","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":"2026-07-05T01:14:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hCpN/jG0oS7RMWVC2IWD95VvGy3GCi2pjzS8fIsmx/UsV1RvVO1yWb33wAi8wfqVuT8EGda1UNmZOpmZxwnuDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:52:31.390525Z"},"content_sha256":"a845f0a6bfa678f3399ecc025dab69de05a67f718bf87a4f63d8fe8d9895a9f2","schema_version":"1.0","event_id":"sha256:a845f0a6bfa678f3399ecc025dab69de05a67f718bf87a4f63d8fe8d9895a9f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:5B4I4DYOKYNJUJSLKCEQGEHSTA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander J. Smola, Pratik Chaudhari, Rasool Fakoor","submitted_at":"2020-06-26T20:21:12Z","abstract_excerpt":"This paper prescribes a suite of techniques for off-policy Reinforcement Learning (RL) that simplify the training process and reduce the sample complexity. First, we show that simple Deterministic Policy Gradient works remarkably well as long as the overestimation bias is controlled. This is contrast to existing literature which creates sophisticated off-policy techniques. Second, we pinpoint training instabilities, typical of off-policy algorithms, to the greedy policy update step; existing solutions such as delayed policy updates do not mitigate this issue. Third, we show that ideas in the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15199","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/2006.15199/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":"2026-07-05T01:14:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MLsxWdDW9wq4mSo4hzdU/H0Z+YBGx7eiPbCgkJbK+X25cwD4AWO/OBTQCJeIR8pJ0BdZyFs4vIhopDyqc/VOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:52:31.391445Z"},"content_sha256":"dd533fdbd5e011a7df0bbb52ddd7fa98a33d6295864437b955f14b5d3b21200f","schema_version":"1.0","event_id":"sha256:dd533fdbd5e011a7df0bbb52ddd7fa98a33d6295864437b955f14b5d3b21200f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5B4I4DYOKYNJUJSLKCEQGEHSTA/bundle.json","state_url":"https://pith.science/pith/5B4I4DYOKYNJUJSLKCEQGEHSTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5B4I4DYOKYNJUJSLKCEQGEHSTA/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":"2026-08-05T20:52:31Z","links":{"resolver":"https://pith.science/pith/5B4I4DYOKYNJUJSLKCEQGEHSTA","bundle":"https://pith.science/pith/5B4I4DYOKYNJUJSLKCEQGEHSTA/bundle.json","state":"https://pith.science/pith/5B4I4DYOKYNJUJSLKCEQGEHSTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5B4I4DYOKYNJUJSLKCEQGEHSTA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5B4I4DYOKYNJUJSLKCEQGEHSTA","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":"ec081b6d2ebdab1463c23b58a389ae6f0ae8488906e34cae14b75725c878f60e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-26T20:21:12Z","title_canon_sha256":"7c71eb4d92b2e00d630b448b67fb2baec8e42d13bcf215b122b032bdd1f83739"},"schema_version":"1.0","source":{"id":"2006.15199","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.15199","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"arxiv_version","alias_value":"2006.15199v1","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15199","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"pith_short_12","alias_value":"5B4I4DYOKYNJ","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"pith_short_16","alias_value":"5B4I4DYOKYNJUJSL","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"pith_short_8","alias_value":"5B4I4DYO","created_at":"2026-07-05T01:14:03Z"}],"graph_snapshots":[{"event_id":"sha256:dd533fdbd5e011a7df0bbb52ddd7fa98a33d6295864437b955f14b5d3b21200f","target":"graph","created_at":"2026-07-05T01:14:03Z","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/2006.15199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper prescribes a suite of techniques for off-policy Reinforcement Learning (RL) that simplify the training process and reduce the sample complexity. First, we show that simple Deterministic Policy Gradient works remarkably well as long as the overestimation bias is controlled. This is contrast to existing literature which creates sophisticated off-policy techniques. Second, we pinpoint training instabilities, typical of off-policy algorithms, to the greedy policy update step; existing solutions such as delayed policy updates do not mitigate this issue. Third, we show that ideas in the p","authors_text":"Alexander J. Smola, Pratik Chaudhari, Rasool Fakoor","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-26T20:21:12Z","title":"DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15199","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:a845f0a6bfa678f3399ecc025dab69de05a67f718bf87a4f63d8fe8d9895a9f2","target":"record","created_at":"2026-07-05T01:14:03Z","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":"ec081b6d2ebdab1463c23b58a389ae6f0ae8488906e34cae14b75725c878f60e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-26T20:21:12Z","title_canon_sha256":"7c71eb4d92b2e00d630b448b67fb2baec8e42d13bcf215b122b032bdd1f83739"},"schema_version":"1.0","source":{"id":"2006.15199","kind":"arxiv","version":1}},"canonical_sha256":"e8788e0f0e561a9a264b50890310f2982aad45168fa29ff8924ecc23a4a51b3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8788e0f0e561a9a264b50890310f2982aad45168fa29ff8924ecc23a4a51b3d","first_computed_at":"2026-07-05T01:14:03.070039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:14:03.070039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Xj/a1DJ2QgAn3x182IikQEJKihKEJBf5n4U/RxmcLzu4YWWlnWY1MbnXAaxJELv9BSWZwK4NBZczOUk6Y/eDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:14:03.070462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.15199","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a845f0a6bfa678f3399ecc025dab69de05a67f718bf87a4f63d8fe8d9895a9f2","sha256:dd533fdbd5e011a7df0bbb52ddd7fa98a33d6295864437b955f14b5d3b21200f"],"state_sha256":"1feba7f93a998b0e207729ffff05e10a8d0c0204958e53f548a6861def053643"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0PTueOaIVl43jC3Ku88iZ6ECUCsbSpuQ3SLa4SkuFp75iK0h2s+/uJopeXgRw0cPdBd2vaF+vD0yccgQkWPNBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:52:31.397401Z","bundle_sha256":"b9627067e68a7e0bf4b21b7fde3e6a7531cd1bffab190d20e0bdd6c64b43c6d5"}}