{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4S5CSC3E5JNA7BMP6KJMFOFFWK","short_pith_number":"pith:4S5CSC3E","canonical_record":{"source":{"id":"1910.09959","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-10-19T03:37:05Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"1c8bc693b596058b60020544a8b628a1390766c1ef2a8a841f1693e4b693ee68","abstract_canon_sha256":"8b076d660b5dc25faa463bba3e49dd3721abf3b4d288285d081a68e77b5c3558"},"schema_version":"1.0"},"canonical_sha256":"e4ba290b64ea5a0f858ff292c2b8a5b2a58043118d7e9e5a0a9ba9127fc21fe4","source":{"kind":"arxiv","id":"1910.09959","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.09959","created_at":"2026-07-05T00:19:21Z"},{"alias_kind":"arxiv_version","alias_value":"1910.09959v3","created_at":"2026-07-05T00:19:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.09959","created_at":"2026-07-05T00:19:21Z"},{"alias_kind":"pith_short_12","alias_value":"4S5CSC3E5JNA","created_at":"2026-07-05T00:19:21Z"},{"alias_kind":"pith_short_16","alias_value":"4S5CSC3E5JNA7BMP","created_at":"2026-07-05T00:19:21Z"},{"alias_kind":"pith_short_8","alias_value":"4S5CSC3E","created_at":"2026-07-05T00:19:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4S5CSC3E5JNA7BMP6KJMFOFFWK","target":"record","payload":{"canonical_record":{"source":{"id":"1910.09959","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-10-19T03:37:05Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"1c8bc693b596058b60020544a8b628a1390766c1ef2a8a841f1693e4b693ee68","abstract_canon_sha256":"8b076d660b5dc25faa463bba3e49dd3721abf3b4d288285d081a68e77b5c3558"},"schema_version":"1.0"},"canonical_sha256":"e4ba290b64ea5a0f858ff292c2b8a5b2a58043118d7e9e5a0a9ba9127fc21fe4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:21.804399Z","signature_b64":"6QDw0fEDJb4JzxFNthoeNR1fP2srT757ZDaJBZvPBkyNRj60Ah77nfXqNe0NKhQvcJyWOLm6yQ4SCG5tzTrXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4ba290b64ea5a0f858ff292c2b8a5b2a58043118d7e9e5a0a9ba9127fc21fe4","last_reissued_at":"2026-07-05T00:19:21.803958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:21.803958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.09959","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:19:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PP0mCeKbvlaNMUk6nYp2SQmSYhk1E7ZeH4lQ0hPr9jMncnbuY86AUe/E+gmG83YOVDdFlqBmB4oHlIaxSQmNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:17:44.520127Z"},"content_sha256":"2f72fcfb4f0645f64afb01ee7d1797b41bfd651abfad5049595746b51d7daeee","schema_version":"1.0","event_id":"sha256:2f72fcfb4f0645f64afb01ee7d1797b41bfd651abfad5049595746b51d7daeee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4S5CSC3E5JNA7BMP6KJMFOFFWK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards More Sample Efficiency in Reinforcement Learning with Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Jiancong Huang, Juan Rojas, Matthieu Zimmer, Paul Weng, Yijiong Lin","submitted_at":"2019-10-19T03:37:05Z","abstract_excerpt":"Deep reinforcement learning (DRL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. We propose two novel data augmentation techniques for DRL in order to reuse more efficiently observed data. The first one called Kaleidoscope Experience Replay exploits reflectional symmetries, while the second called Goal-augmented Experience Replay takes advantage of lax goal definitions. Our preliminary experimental results show a large increase in learning speed."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.09959","kind":"arxiv","version":3},"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/1910.09959/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":"2026-07-05T00:19:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ddbiWn75N5YdNrxFESTHoijHfslKU+y5k22/sVKv49v0g/nVCCqYKvpe0V8Rx1T4V8u25sVbuMzQqmIVqh+1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:17:44.520510Z"},"content_sha256":"9210ec3015169c1a3d595eef40a8751a54f1f6111038bac506c7b87659fb97ff","schema_version":"1.0","event_id":"sha256:9210ec3015169c1a3d595eef40a8751a54f1f6111038bac506c7b87659fb97ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4S5CSC3E5JNA7BMP6KJMFOFFWK/bundle.json","state_url":"https://pith.science/pith/4S5CSC3E5JNA7BMP6KJMFOFFWK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4S5CSC3E5JNA7BMP6KJMFOFFWK/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":"2026-07-05T09:17:44Z","links":{"resolver":"https://pith.science/pith/4S5CSC3E5JNA7BMP6KJMFOFFWK","bundle":"https://pith.science/pith/4S5CSC3E5JNA7BMP6KJMFOFFWK/bundle.json","state":"https://pith.science/pith/4S5CSC3E5JNA7BMP6KJMFOFFWK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4S5CSC3E5JNA7BMP6KJMFOFFWK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4S5CSC3E5JNA7BMP6KJMFOFFWK","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":"8b076d660b5dc25faa463bba3e49dd3721abf3b4d288285d081a68e77b5c3558","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-10-19T03:37:05Z","title_canon_sha256":"1c8bc693b596058b60020544a8b628a1390766c1ef2a8a841f1693e4b693ee68"},"schema_version":"1.0","source":{"id":"1910.09959","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.09959","created_at":"2026-07-05T00:19:21Z"},{"alias_kind":"arxiv_version","alias_value":"1910.09959v3","created_at":"2026-07-05T00:19:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.09959","created_at":"2026-07-05T00:19:21Z"},{"alias_kind":"pith_short_12","alias_value":"4S5CSC3E5JNA","created_at":"2026-07-05T00:19:21Z"},{"alias_kind":"pith_short_16","alias_value":"4S5CSC3E5JNA7BMP","created_at":"2026-07-05T00:19:21Z"},{"alias_kind":"pith_short_8","alias_value":"4S5CSC3E","created_at":"2026-07-05T00:19:21Z"}],"graph_snapshots":[{"event_id":"sha256:9210ec3015169c1a3d595eef40a8751a54f1f6111038bac506c7b87659fb97ff","target":"graph","created_at":"2026-07-05T00:19:21Z","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/1910.09959/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (DRL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. We propose two novel data augmentation techniques for DRL in order to reuse more efficiently observed data. The first one called Kaleidoscope Experience Replay exploits reflectional symmetries, while the second called Goal-augmented Experience Replay takes advantage of lax goal definitions. Our preliminary experimental results show a large increase in learning speed.","authors_text":"Jiancong Huang, Juan Rojas, Matthieu Zimmer, Paul Weng, Yijiong Lin","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-10-19T03:37:05Z","title":"Towards More Sample Efficiency in Reinforcement Learning with Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.09959","kind":"arxiv","version":3},"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":"sha256:2f72fcfb4f0645f64afb01ee7d1797b41bfd651abfad5049595746b51d7daeee","target":"record","created_at":"2026-07-05T00:19:21Z","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":"8b076d660b5dc25faa463bba3e49dd3721abf3b4d288285d081a68e77b5c3558","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-10-19T03:37:05Z","title_canon_sha256":"1c8bc693b596058b60020544a8b628a1390766c1ef2a8a841f1693e4b693ee68"},"schema_version":"1.0","source":{"id":"1910.09959","kind":"arxiv","version":3}},"canonical_sha256":"e4ba290b64ea5a0f858ff292c2b8a5b2a58043118d7e9e5a0a9ba9127fc21fe4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4ba290b64ea5a0f858ff292c2b8a5b2a58043118d7e9e5a0a9ba9127fc21fe4","first_computed_at":"2026-07-05T00:19:21.803958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:19:21.803958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6QDw0fEDJb4JzxFNthoeNR1fP2srT757ZDaJBZvPBkyNRj60Ah77nfXqNe0NKhQvcJyWOLm6yQ4SCG5tzTrXDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:19:21.804399Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.09959","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f72fcfb4f0645f64afb01ee7d1797b41bfd651abfad5049595746b51d7daeee","sha256:9210ec3015169c1a3d595eef40a8751a54f1f6111038bac506c7b87659fb97ff"],"state_sha256":"da765d8f0f035190ef91d54c14b045d481784978d0a43aa4c313575d43126222"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DvK4+mpeifDb5Fsce90m4pvxngBNf3WxbMhqZrhZCYeI48lTexPUlSd/TZtiVTesxUmP6BhWScXgYxxqlbVHBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T09:17:44.522490Z","bundle_sha256":"ebd94c83892fbd2fd5656a4362de5288b98e34223874bf482dee020f46929630"}}