{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2B6B23YXAJ6DPHYJFIZCOTVGTQ","short_pith_number":"pith:2B6B23YX","canonical_record":{"source":{"id":"1810.01363","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T16:42:35Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0b1741a6095cb2b9c428e9a82c0bdf26677cf393a9929153c40bb4680f8cb126","abstract_canon_sha256":"dfa843533e25579686595e2ce299bcd0c9cca250c84a01473698be475885fb64"},"schema_version":"1.0"},"canonical_sha256":"d07c1d6f17027c379f092a32274ea69c01ed4ef0ea7e9df8c9658ff657430ead","source":{"kind":"arxiv","id":"1810.01363","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.01363","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"1810.01363v5","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01363","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"2B6B23YXAJ6D","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"2B6B23YXAJ6DPHYJ","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"2B6B23YX","created_at":"2026-07-05T01:05:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2B6B23YXAJ6DPHYJFIZCOTVGTQ","target":"record","payload":{"canonical_record":{"source":{"id":"1810.01363","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T16:42:35Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0b1741a6095cb2b9c428e9a82c0bdf26677cf393a9929153c40bb4680f8cb126","abstract_canon_sha256":"dfa843533e25579686595e2ce299bcd0c9cca250c84a01473698be475885fb64"},"schema_version":"1.0"},"canonical_sha256":"d07c1d6f17027c379f092a32274ea69c01ed4ef0ea7e9df8c9658ff657430ead","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:08.453788Z","signature_b64":"Xe7c/TpwK3T9mtLSmMJ9TGegOlnvr4LVs+nfcKGWuY9SweeDOn9EllpONj2klMbHiJ472KN10Y/f1m3bYB6RAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d07c1d6f17027c379f092a32274ea69c01ed4ef0ea7e9df8c9658ff657430ead","last_reissued_at":"2026-07-05T01:05:08.453399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:08.453399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.01363","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yiU+CR3VO7qXJS1pXfmqCm9NE+9i/MUAjXnKOPbAbo6qaavf3SvZgmn6tZzsy/JJGwFQN3ezZg5qfahvgdUODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:04:22.445448Z"},"content_sha256":"70a8a36c62de65a82c19e3e91944087dbbdbaf0f9395b09a5dc16d426b972f1e","schema_version":"1.0","event_id":"sha256:70a8a36c62de65a82c19e3e91944087dbbdbaf0f9395b09a5dc16d426b972f1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2B6B23YXAJ6DPHYJFIZCOTVGTQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Energy-Based Hindsight Experience Prioritization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rui Zhao, Volker Tresp","submitted_at":"2018-10-02T16:42:35Z","abstract_excerpt":"In Hindsight Experience Replay (HER), a reinforcement learning agent is trained by treating whatever it has achieved as virtual goals. However, in previous work, the experience was replayed at random, without considering which episode might be the most valuable for learning. In this paper, we develop an energy-based framework for prioritizing hindsight experience in robotic manipulation tasks. Our approach is inspired by the work-energy principle in physics. We define a trajectory energy function as the sum of the transition energy of the target object over the trajectory. We hypothesize that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01363","kind":"arxiv","version":5},"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/1810.01363/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":"2026-07-05T01:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vW+TUTUeMoE5+5CIyx2Q3d0bCxreoun6m63UcynNdW9iHPxbMiqOkmiA/0fSKKaqQA3rVSZL3QHyyXlGUMSlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:04:22.446405Z"},"content_sha256":"8d0c95d592565a7291c8bc2bd7c60dd8a70d2e7a858bdb0b2dee2bc0522a846d","schema_version":"1.0","event_id":"sha256:8d0c95d592565a7291c8bc2bd7c60dd8a70d2e7a858bdb0b2dee2bc0522a846d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2B6B23YXAJ6DPHYJFIZCOTVGTQ/bundle.json","state_url":"https://pith.science/pith/2B6B23YXAJ6DPHYJFIZCOTVGTQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2B6B23YXAJ6DPHYJFIZCOTVGTQ/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":"2026-08-17T05:04:22Z","links":{"resolver":"https://pith.science/pith/2B6B23YXAJ6DPHYJFIZCOTVGTQ","bundle":"https://pith.science/pith/2B6B23YXAJ6DPHYJFIZCOTVGTQ/bundle.json","state":"https://pith.science/pith/2B6B23YXAJ6DPHYJFIZCOTVGTQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2B6B23YXAJ6DPHYJFIZCOTVGTQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2B6B23YXAJ6DPHYJFIZCOTVGTQ","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":"dfa843533e25579686595e2ce299bcd0c9cca250c84a01473698be475885fb64","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T16:42:35Z","title_canon_sha256":"0b1741a6095cb2b9c428e9a82c0bdf26677cf393a9929153c40bb4680f8cb126"},"schema_version":"1.0","source":{"id":"1810.01363","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.01363","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"1810.01363v5","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01363","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"2B6B23YXAJ6D","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"2B6B23YXAJ6DPHYJ","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"2B6B23YX","created_at":"2026-07-05T01:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:8d0c95d592565a7291c8bc2bd7c60dd8a70d2e7a858bdb0b2dee2bc0522a846d","target":"graph","created_at":"2026-07-05T01:05:08Z","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/1810.01363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Hindsight Experience Replay (HER), a reinforcement learning agent is trained by treating whatever it has achieved as virtual goals. However, in previous work, the experience was replayed at random, without considering which episode might be the most valuable for learning. In this paper, we develop an energy-based framework for prioritizing hindsight experience in robotic manipulation tasks. Our approach is inspired by the work-energy principle in physics. We define a trajectory energy function as the sum of the transition energy of the target object over the trajectory. We hypothesize that ","authors_text":"Rui Zhao, Volker Tresp","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T16:42:35Z","title":"Energy-Based Hindsight Experience Prioritization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01363","kind":"arxiv","version":5},"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":"sha256:70a8a36c62de65a82c19e3e91944087dbbdbaf0f9395b09a5dc16d426b972f1e","target":"record","created_at":"2026-07-05T01:05:08Z","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":"dfa843533e25579686595e2ce299bcd0c9cca250c84a01473698be475885fb64","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T16:42:35Z","title_canon_sha256":"0b1741a6095cb2b9c428e9a82c0bdf26677cf393a9929153c40bb4680f8cb126"},"schema_version":"1.0","source":{"id":"1810.01363","kind":"arxiv","version":5}},"canonical_sha256":"d07c1d6f17027c379f092a32274ea69c01ed4ef0ea7e9df8c9658ff657430ead","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d07c1d6f17027c379f092a32274ea69c01ed4ef0ea7e9df8c9658ff657430ead","first_computed_at":"2026-07-05T01:05:08.453399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:08.453399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xe7c/TpwK3T9mtLSmMJ9TGegOlnvr4LVs+nfcKGWuY9SweeDOn9EllpONj2klMbHiJ472KN10Y/f1m3bYB6RAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:08.453788Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.01363","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70a8a36c62de65a82c19e3e91944087dbbdbaf0f9395b09a5dc16d426b972f1e","sha256:8d0c95d592565a7291c8bc2bd7c60dd8a70d2e7a858bdb0b2dee2bc0522a846d"],"state_sha256":"6e8a54571b1bd4334473c348dc8b9b4e1033134e711c06c2932171849b4927c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1c/hx53VBWR9/wUeU/1NDBTv3KE8NDnbE+K5cREk62cNy2LHVD+edIP5ZDjDKb1ymd7YZ9hiW9SlxGTT42lHAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T05:04:22.456554Z","bundle_sha256":"dc9e9fe5ac66117eb0ed1d5e8b6e317859a917adce6a0c7fcca0c0d9c9ac64fe"}}