{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:DZ4K6F2K6GWQL6B4EVBOMO3QYK","short_pith_number":"pith:DZ4K6F2K","canonical_record":{"source":{"id":"1710.04423","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-12T09:42:47Z","cross_cats_sorted":[],"title_canon_sha256":"37588c497ce1a7d3d23ad51b0205b260b63136c3338e14e92bc46cc4c7a5d294","abstract_canon_sha256":"a594cc962ef5902ad4eff56796edeb56cab74be6c18651e0474314182ccea46c"},"schema_version":"1.0"},"canonical_sha256":"1e78af174af1ad05f83c2542e63b70c2bc9af1756357dc6c120928e63f741267","source":{"kind":"arxiv","id":"1710.04423","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.04423","created_at":"2026-05-18T00:04:23Z"},{"alias_kind":"arxiv_version","alias_value":"1710.04423v2","created_at":"2026-05-18T00:04:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04423","created_at":"2026-05-18T00:04:23Z"},{"alias_kind":"pith_short_12","alias_value":"DZ4K6F2K6GWQ","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"DZ4K6F2K6GWQL6B4","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"DZ4K6F2K","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:DZ4K6F2K6GWQL6B4EVBOMO3QYK","target":"record","payload":{"canonical_record":{"source":{"id":"1710.04423","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-12T09:42:47Z","cross_cats_sorted":[],"title_canon_sha256":"37588c497ce1a7d3d23ad51b0205b260b63136c3338e14e92bc46cc4c7a5d294","abstract_canon_sha256":"a594cc962ef5902ad4eff56796edeb56cab74be6c18651e0474314182ccea46c"},"schema_version":"1.0"},"canonical_sha256":"1e78af174af1ad05f83c2542e63b70c2bc9af1756357dc6c120928e63f741267","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:23.979534Z","signature_b64":"hKfHRwmGtF6hnnnnNOGTmLHkUdHyo8aQTnJIvzerunRITanwJcA+rZnRdWY6BxACnEz4U8lZaWxGE6jhx7XoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e78af174af1ad05f83c2542e63b70c2bc9af1756357dc6c120928e63f741267","last_reissued_at":"2026-05-18T00:04:23.979020Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:23.979020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.04423","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":"2026-05-18T00:04:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j5rwajLquT8cI4tnDiKJ3iTlVYcv+nTuMHkl3E/DExV2e9vAYEi33hFt5RxbJKS29E3Mb1dWKTrkXngpSpzECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:57:33.823368Z"},"content_sha256":"682a425436e3fe28dd9f46355804b54bec85e5b1eea748d64207d57b3c601b1d","schema_version":"1.0","event_id":"sha256:682a425436e3fe28dd9f46355804b54bec85e5b1eea748d64207d57b3c601b1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:DZ4K6F2K6GWQL6B4EVBOMO3QYK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AMBER: Adaptive Multi-Batch Experience Replay for Continuous Action Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Seungyul Han, Youngchul Sung","submitted_at":"2017-10-12T09:42:47Z","abstract_excerpt":"In this paper, a new adaptive multi-batch experience replay scheme is proposed for proximal policy optimization (PPO) for continuous action control. On the contrary to original PPO, the proposed scheme uses the batch samples of past policies as well as the current policy for the update for the next policy, where the number of the used past batches is adaptively determined based on the oldness of the past batches measured by the average importance sampling (IS) weight. The new algorithm constructed by combining PPO with the proposed multi-batch experience replay scheme maintains the advantages "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04423","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":"2026-05-18T00:04:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zxgyIuzQ7jywfba4nGvpzZ/MwIXkGbDLeSwYmxSWPU+hjSEKqwH34H//BBxeCJY6VwjTt5/WSbCpJN6tXEtMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:57:33.823709Z"},"content_sha256":"efcd6056320fedb5b23a1d8f0e7ee346b5a88b7547c9c82ba4cf137982f8144f","schema_version":"1.0","event_id":"sha256:efcd6056320fedb5b23a1d8f0e7ee346b5a88b7547c9c82ba4cf137982f8144f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DZ4K6F2K6GWQL6B4EVBOMO3QYK/bundle.json","state_url":"https://pith.science/pith/DZ4K6F2K6GWQL6B4EVBOMO3QYK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DZ4K6F2K6GWQL6B4EVBOMO3QYK/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":"2026-05-31T09:57:33Z","links":{"resolver":"https://pith.science/pith/DZ4K6F2K6GWQL6B4EVBOMO3QYK","bundle":"https://pith.science/pith/DZ4K6F2K6GWQL6B4EVBOMO3QYK/bundle.json","state":"https://pith.science/pith/DZ4K6F2K6GWQL6B4EVBOMO3QYK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DZ4K6F2K6GWQL6B4EVBOMO3QYK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:DZ4K6F2K6GWQL6B4EVBOMO3QYK","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":"a594cc962ef5902ad4eff56796edeb56cab74be6c18651e0474314182ccea46c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-12T09:42:47Z","title_canon_sha256":"37588c497ce1a7d3d23ad51b0205b260b63136c3338e14e92bc46cc4c7a5d294"},"schema_version":"1.0","source":{"id":"1710.04423","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.04423","created_at":"2026-05-18T00:04:23Z"},{"alias_kind":"arxiv_version","alias_value":"1710.04423v2","created_at":"2026-05-18T00:04:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04423","created_at":"2026-05-18T00:04:23Z"},{"alias_kind":"pith_short_12","alias_value":"DZ4K6F2K6GWQ","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"DZ4K6F2K6GWQL6B4","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"DZ4K6F2K","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:efcd6056320fedb5b23a1d8f0e7ee346b5a88b7547c9c82ba4cf137982f8144f","target":"graph","created_at":"2026-05-18T00:04:23Z","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":"In this paper, a new adaptive multi-batch experience replay scheme is proposed for proximal policy optimization (PPO) for continuous action control. On the contrary to original PPO, the proposed scheme uses the batch samples of past policies as well as the current policy for the update for the next policy, where the number of the used past batches is adaptively determined based on the oldness of the past batches measured by the average importance sampling (IS) weight. The new algorithm constructed by combining PPO with the proposed multi-batch experience replay scheme maintains the advantages ","authors_text":"Seungyul Han, Youngchul Sung","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-12T09:42:47Z","title":"AMBER: Adaptive Multi-Batch Experience Replay for Continuous Action Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04423","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":"sha256:682a425436e3fe28dd9f46355804b54bec85e5b1eea748d64207d57b3c601b1d","target":"record","created_at":"2026-05-18T00:04:23Z","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":"a594cc962ef5902ad4eff56796edeb56cab74be6c18651e0474314182ccea46c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-12T09:42:47Z","title_canon_sha256":"37588c497ce1a7d3d23ad51b0205b260b63136c3338e14e92bc46cc4c7a5d294"},"schema_version":"1.0","source":{"id":"1710.04423","kind":"arxiv","version":2}},"canonical_sha256":"1e78af174af1ad05f83c2542e63b70c2bc9af1756357dc6c120928e63f741267","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e78af174af1ad05f83c2542e63b70c2bc9af1756357dc6c120928e63f741267","first_computed_at":"2026-05-18T00:04:23.979020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:23.979020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hKfHRwmGtF6hnnnnNOGTmLHkUdHyo8aQTnJIvzerunRITanwJcA+rZnRdWY6BxACnEz4U8lZaWxGE6jhx7XoAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:23.979534Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.04423","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:682a425436e3fe28dd9f46355804b54bec85e5b1eea748d64207d57b3c601b1d","sha256:efcd6056320fedb5b23a1d8f0e7ee346b5a88b7547c9c82ba4cf137982f8144f"],"state_sha256":"33da1ad63a1c23abfb6ab99b5508ed70a874080d86b35d05f7f3fb309c531168"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K8AtBGt+Vu/b3gA5CgbScRawih2sIy8srHH6GWYEVjfAIZiUbYpebEhcW2yCh9MeiLNoHE7Ib+fKfcakCS4ZDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T09:57:33.825507Z","bundle_sha256":"4549e69989f89f7ad3f6d13e687095e69857ffc5584c5af81618618dde6eb39a"}}