{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HJEMFWEDBZRMNL3NNLMWED43UU","short_pith_number":"pith:HJEMFWED","canonical_record":{"source":{"id":"1809.09501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T14:04:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"66afb8278665fc1d2b8c5b65e2452e476e595a160ef9061363b80d94dea9ba5b","abstract_canon_sha256":"8b91f33c472c52f1767917e5f17a3b1d17b8219f1b74d8803969888354f8fe2a"},"schema_version":"1.0"},"canonical_sha256":"3a48c2d8830e62c6af6d6ad9620f9ba50fecdbb4e5ed2a37a395d6cf1662e63b","source":{"kind":"arxiv","id":"1809.09501","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.09501","created_at":"2026-05-18T00:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"1809.09501v1","created_at":"2026-05-18T00:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09501","created_at":"2026-05-18T00:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"HJEMFWEDBZRM","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HJEMFWEDBZRMNL3N","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HJEMFWED","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HJEMFWEDBZRMNL3NNLMWED43UU","target":"record","payload":{"canonical_record":{"source":{"id":"1809.09501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T14:04:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"66afb8278665fc1d2b8c5b65e2452e476e595a160ef9061363b80d94dea9ba5b","abstract_canon_sha256":"8b91f33c472c52f1767917e5f17a3b1d17b8219f1b74d8803969888354f8fe2a"},"schema_version":"1.0"},"canonical_sha256":"3a48c2d8830e62c6af6d6ad9620f9ba50fecdbb4e5ed2a37a395d6cf1662e63b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:51.008573Z","signature_b64":"ZyXxHs9+VhgK91/AObc247TtH+qyWm+hFNAHoB/XD1PDN87PuvDRRkTOAPH8vLDd092+DIzNYCx4TBHUF8oPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a48c2d8830e62c6af6d6ad9620f9ba50fecdbb4e5ed2a37a395d6cf1662e63b","last_reissued_at":"2026-05-18T00:04:51.008113Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:51.008113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.09501","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":"2026-05-18T00:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7m+/kncFMdFi8aEnFxhDcgEzeZ7C+Xv5EhDAMB4YhpQ9aVwkPwyoKgxv9Z9pq3+ujjQ6p3Y10LaIdSt2AfjdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T23:26:51.795264Z"},"content_sha256":"37ba279785d738d475134d7e213ad1cea7548fe310fbea5ec739772bfa18108b","schema_version":"1.0","event_id":"sha256:37ba279785d738d475134d7e213ad1cea7548fe310fbea5ec739772bfa18108b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HJEMFWEDBZRMNL3NNLMWED43UU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Anderson Acceleration for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bruno Scherrer, Matthieu Geist","submitted_at":"2018-09-25T14:04:25Z","abstract_excerpt":"Anderson acceleration is an old and simple method for accelerating the computation of a fixed point. However, as far as we know and quite surprisingly, it has never been applied to dynamic programming or reinforcement learning. In this paper, we explain briefly what Anderson acceleration is and how it can be applied to value iteration, this being supported by preliminary experiments showing a significant speed up of convergence, that we critically discuss. We also discuss how this idea could be applied more generally to (deep) reinforcement learning."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09501","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":"2026-05-18T00:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x7SSNzyElsK86UVxEkZyD56heD02QIO9CscEEhzj9pzvuCm2qo85Z3LyH+ynymo9Ut2Gc6uG5AI3puD9An0WCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T23:26:51.795973Z"},"content_sha256":"e07db6a9f76c7f63fea3db48187871368bcdf206c313dfd2032f3cb344b11814","schema_version":"1.0","event_id":"sha256:e07db6a9f76c7f63fea3db48187871368bcdf206c313dfd2032f3cb344b11814"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HJEMFWEDBZRMNL3NNLMWED43UU/bundle.json","state_url":"https://pith.science/pith/HJEMFWEDBZRMNL3NNLMWED43UU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HJEMFWEDBZRMNL3NNLMWED43UU/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":"2026-05-31T23:26:51Z","links":{"resolver":"https://pith.science/pith/HJEMFWEDBZRMNL3NNLMWED43UU","bundle":"https://pith.science/pith/HJEMFWEDBZRMNL3NNLMWED43UU/bundle.json","state":"https://pith.science/pith/HJEMFWEDBZRMNL3NNLMWED43UU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HJEMFWEDBZRMNL3NNLMWED43UU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HJEMFWEDBZRMNL3NNLMWED43UU","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":"8b91f33c472c52f1767917e5f17a3b1d17b8219f1b74d8803969888354f8fe2a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T14:04:25Z","title_canon_sha256":"66afb8278665fc1d2b8c5b65e2452e476e595a160ef9061363b80d94dea9ba5b"},"schema_version":"1.0","source":{"id":"1809.09501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.09501","created_at":"2026-05-18T00:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"1809.09501v1","created_at":"2026-05-18T00:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09501","created_at":"2026-05-18T00:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"HJEMFWEDBZRM","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HJEMFWEDBZRMNL3N","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HJEMFWED","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:e07db6a9f76c7f63fea3db48187871368bcdf206c313dfd2032f3cb344b11814","target":"graph","created_at":"2026-05-18T00:04:51Z","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":"Anderson acceleration is an old and simple method for accelerating the computation of a fixed point. However, as far as we know and quite surprisingly, it has never been applied to dynamic programming or reinforcement learning. In this paper, we explain briefly what Anderson acceleration is and how it can be applied to value iteration, this being supported by preliminary experiments showing a significant speed up of convergence, that we critically discuss. We also discuss how this idea could be applied more generally to (deep) reinforcement learning.","authors_text":"Bruno Scherrer, Matthieu Geist","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T14:04:25Z","title":"Anderson Acceleration for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09501","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":"sha256:37ba279785d738d475134d7e213ad1cea7548fe310fbea5ec739772bfa18108b","target":"record","created_at":"2026-05-18T00:04:51Z","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":"8b91f33c472c52f1767917e5f17a3b1d17b8219f1b74d8803969888354f8fe2a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T14:04:25Z","title_canon_sha256":"66afb8278665fc1d2b8c5b65e2452e476e595a160ef9061363b80d94dea9ba5b"},"schema_version":"1.0","source":{"id":"1809.09501","kind":"arxiv","version":1}},"canonical_sha256":"3a48c2d8830e62c6af6d6ad9620f9ba50fecdbb4e5ed2a37a395d6cf1662e63b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a48c2d8830e62c6af6d6ad9620f9ba50fecdbb4e5ed2a37a395d6cf1662e63b","first_computed_at":"2026-05-18T00:04:51.008113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:51.008113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZyXxHs9+VhgK91/AObc247TtH+qyWm+hFNAHoB/XD1PDN87PuvDRRkTOAPH8vLDd092+DIzNYCx4TBHUF8oPAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:51.008573Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.09501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37ba279785d738d475134d7e213ad1cea7548fe310fbea5ec739772bfa18108b","sha256:e07db6a9f76c7f63fea3db48187871368bcdf206c313dfd2032f3cb344b11814"],"state_sha256":"7146d92d5cd8093eb8f7aba576eb5ecc3af60b4bf90909e03281d9d296f43807"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cYZc0mIA0X/JnIptFQxeloJRZTGhX4gSMTqT+9HSJC2qHJZ9tF9/5jMkcAa9D2r/aCdnzg9AMMx3msq0rVaeDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T23:26:51.799346Z","bundle_sha256":"53c16bb7391b2f2ac76d9db6db9610cd3d14d2069577251a0133680afd682c08"}}