{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:55EG7L3FJBNIGGHEDWEZSXELHD","short_pith_number":"pith:55EG7L3F","canonical_record":{"source":{"id":"1802.04821","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-13T19:07:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2baf221de14826c3475cd69e1b0d06a290ecf7fea948b06dcc1f94f3489ed8a8","abstract_canon_sha256":"66ef04f1ef3d4ae97f5c84d5f628606d5c6627e6efa57f89e7a6f2cdf9fbb7c0"},"schema_version":"1.0"},"canonical_sha256":"ef486faf65485a8318e41d89995c8b38d5ffbe619bde5467c7996542abf81022","source":{"kind":"arxiv","id":"1802.04821","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04821","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04821v2","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04821","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"55EG7L3FJBNI","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"55EG7L3FJBNIGGHE","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"55EG7L3F","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:55EG7L3FJBNIGGHEDWEZSXELHD","target":"record","payload":{"canonical_record":{"source":{"id":"1802.04821","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-13T19:07:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2baf221de14826c3475cd69e1b0d06a290ecf7fea948b06dcc1f94f3489ed8a8","abstract_canon_sha256":"66ef04f1ef3d4ae97f5c84d5f628606d5c6627e6efa57f89e7a6f2cdf9fbb7c0"},"schema_version":"1.0"},"canonical_sha256":"ef486faf65485a8318e41d89995c8b38d5ffbe619bde5467c7996542abf81022","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:18.590299Z","signature_b64":"9OnQ0ivrNH0s4+6ALH1m90aHm/C0Fjb6hgWPn49f0XGzw3gp166xpIFWT3cVhL6sZ9FQTDQkzJhKNrlZ/bfmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef486faf65485a8318e41d89995c8b38d5ffbe619bde5467c7996542abf81022","last_reissued_at":"2026-05-18T00:17:18.589806Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:18.589806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.04821","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":"2026-05-18T00:17:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KzZI6G1JXSkFQW11ly9fX0KlOaiGYmHilmBNbgiQE574DA7qDr4hN9ilfqQn/r8Mg0DAsh4Pi0+DKffLrr7gCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:43:02.776522Z"},"content_sha256":"11644b50257377421b7f96c6fd1f8fb99d13ce2c280f2aa8c580377438fedb59","schema_version":"1.0","event_id":"sha256:11644b50257377421b7f96c6fd1f8fb99d13ce2c280f2aa8c580377438fedb59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:55EG7L3FJBNIGGHEDWEZSXELHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evolved Policy Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bradly C. Stadie, Filip Wolski, Jonathan Ho, Phillip Isola, Pieter Abbeel, Rein Houthooft, Richard Y. Chen","submitted_at":"2018-02-13T19:07:43Z","abstract_excerpt":"We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms. The idea is to evolve a differentiable loss function, such that an agent, which optimizes its policy to minimize this loss, will achieve high rewards. The loss is parametrized via temporal convolutions over the agent's experience. Because this loss is highly flexible in its ability to take into account the agent's history, it enables fast task learning. Empirical results show that our evolved policy gradient algorithm (EPG) achieves faster learning on several randomized environments compared "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04821","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":"2026-05-18T00:17:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Asu9ED3FwDyHRoOSdlp1HaW6FeFpVoKaWuJFp7PwF0RB96Ygvlg6GqpZTdOfM7N32JnWwzeKppyT2plAq2TfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:43:02.776943Z"},"content_sha256":"5851eb895fefb3afd9f5cdcfff1a1a22a67cf70dd956412539ac286024c2f2d0","schema_version":"1.0","event_id":"sha256:5851eb895fefb3afd9f5cdcfff1a1a22a67cf70dd956412539ac286024c2f2d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/55EG7L3FJBNIGGHEDWEZSXELHD/bundle.json","state_url":"https://pith.science/pith/55EG7L3FJBNIGGHEDWEZSXELHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/55EG7L3FJBNIGGHEDWEZSXELHD/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":"2026-05-25T23:43:02Z","links":{"resolver":"https://pith.science/pith/55EG7L3FJBNIGGHEDWEZSXELHD","bundle":"https://pith.science/pith/55EG7L3FJBNIGGHEDWEZSXELHD/bundle.json","state":"https://pith.science/pith/55EG7L3FJBNIGGHEDWEZSXELHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/55EG7L3FJBNIGGHEDWEZSXELHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:55EG7L3FJBNIGGHEDWEZSXELHD","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":"66ef04f1ef3d4ae97f5c84d5f628606d5c6627e6efa57f89e7a6f2cdf9fbb7c0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-13T19:07:43Z","title_canon_sha256":"2baf221de14826c3475cd69e1b0d06a290ecf7fea948b06dcc1f94f3489ed8a8"},"schema_version":"1.0","source":{"id":"1802.04821","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04821","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04821v2","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04821","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"55EG7L3FJBNI","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"55EG7L3FJBNIGGHE","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"55EG7L3F","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:5851eb895fefb3afd9f5cdcfff1a1a22a67cf70dd956412539ac286024c2f2d0","target":"graph","created_at":"2026-05-18T00:17:18Z","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 metalearning approach for learning gradient-based reinforcement learning (RL) algorithms. The idea is to evolve a differentiable loss function, such that an agent, which optimizes its policy to minimize this loss, will achieve high rewards. The loss is parametrized via temporal convolutions over the agent's experience. Because this loss is highly flexible in its ability to take into account the agent's history, it enables fast task learning. Empirical results show that our evolved policy gradient algorithm (EPG) achieves faster learning on several randomized environments compared ","authors_text":"Bradly C. Stadie, Filip Wolski, Jonathan Ho, Phillip Isola, Pieter Abbeel, Rein Houthooft, Richard Y. Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-13T19:07:43Z","title":"Evolved Policy Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04821","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":"sha256:11644b50257377421b7f96c6fd1f8fb99d13ce2c280f2aa8c580377438fedb59","target":"record","created_at":"2026-05-18T00:17:18Z","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":"66ef04f1ef3d4ae97f5c84d5f628606d5c6627e6efa57f89e7a6f2cdf9fbb7c0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-13T19:07:43Z","title_canon_sha256":"2baf221de14826c3475cd69e1b0d06a290ecf7fea948b06dcc1f94f3489ed8a8"},"schema_version":"1.0","source":{"id":"1802.04821","kind":"arxiv","version":2}},"canonical_sha256":"ef486faf65485a8318e41d89995c8b38d5ffbe619bde5467c7996542abf81022","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef486faf65485a8318e41d89995c8b38d5ffbe619bde5467c7996542abf81022","first_computed_at":"2026-05-18T00:17:18.589806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:18.589806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9OnQ0ivrNH0s4+6ALH1m90aHm/C0Fjb6hgWPn49f0XGzw3gp166xpIFWT3cVhL6sZ9FQTDQkzJhKNrlZ/bfmAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:18.590299Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.04821","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11644b50257377421b7f96c6fd1f8fb99d13ce2c280f2aa8c580377438fedb59","sha256:5851eb895fefb3afd9f5cdcfff1a1a22a67cf70dd956412539ac286024c2f2d0"],"state_sha256":"0a9b4c6c86128e9e6f36497c3316a368943e407adb04750bb90119a0f4712ce2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FG3wOYzlU7qsWhuV01zFxQ6nY2EmsFsdqutdi0gC08QRqdtwjibgN0M3fpSUNcCl/BcL8fAbRCHrnlKk0T5MAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:43:02.780276Z","bundle_sha256":"2052303e55de3665aa393dfcf52aea76092bb50be683a2413dfa470f5eef5c77"}}