{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OICWVFXJLHAXVYWTZ6NUT3LOR5","short_pith_number":"pith:OICWVFXJ","schema_version":"1.0","canonical_sha256":"72056a96e959c17ae2d3cf9b49ed6e8f61a47d9d174449409d2a6a49f0ddd8f8","source":{"kind":"arxiv","id":"2401.11372","version":2},"attestation_state":"computed","paper":{"title":"Back-stepping Experience Replay with Application to Model-free Reinforcement Learning for a Soft Snake Robot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Dong Chen, Xiaobo Tan, Xinda Qi, Zhaojian Li","submitted_at":"2024-01-21T02:17:16Z","abstract_excerpt":"In this paper, we propose a novel technique, Back-stepping Experience Replay (BER), that is compatible with arbitrary off-policy reinforcement learning (RL) algorithms. BER aims to enhance learning efficiency in systems with approximate reversibility, reducing the need for complex reward shaping. The method constructs reversed trajectories using back-stepping transitions to reach random or fixed targets. Interpretable as a bi-directional approach, BER addresses inaccuracies in back-stepping transitions through a distillation of the replay experience during learning. Given the intricate nature "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.11372","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-01-21T02:17:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48a7cb39849cdd8d6e3d11290a76c514c6d29d446ffc841f0b14607f018fdd12","abstract_canon_sha256":"ab3d412e6af9860b3ee8109ed11206fd71c7cc1efee1683a77aa02c6729158d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:45.077730Z","signature_b64":"Hk/bpImRnTLpK7GY7SYMOA2HgDQnRVxvJ9w6QPxDaKycwza6727NPcjkR0RvqNzdwD+Kqa4UvO4jhR9aXprcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72056a96e959c17ae2d3cf9b49ed6e8f61a47d9d174449409d2a6a49f0ddd8f8","last_reissued_at":"2026-07-05T09:10:45.077324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:45.077324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Back-stepping Experience Replay with Application to Model-free Reinforcement Learning for a Soft Snake Robot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Dong Chen, Xiaobo Tan, Xinda Qi, Zhaojian Li","submitted_at":"2024-01-21T02:17:16Z","abstract_excerpt":"In this paper, we propose a novel technique, Back-stepping Experience Replay (BER), that is compatible with arbitrary off-policy reinforcement learning (RL) algorithms. BER aims to enhance learning efficiency in systems with approximate reversibility, reducing the need for complex reward shaping. The method constructs reversed trajectories using back-stepping transitions to reach random or fixed targets. Interpretable as a bi-directional approach, BER addresses inaccuracies in back-stepping transitions through a distillation of the replay experience during learning. Given the intricate nature "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11372","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.11372/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.11372","created_at":"2026-07-05T09:10:45.077382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.11372v2","created_at":"2026-07-05T09:10:45.077382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11372","created_at":"2026-07-05T09:10:45.077382+00:00"},{"alias_kind":"pith_short_12","alias_value":"OICWVFXJLHAX","created_at":"2026-07-05T09:10:45.077382+00:00"},{"alias_kind":"pith_short_16","alias_value":"OICWVFXJLHAXVYWT","created_at":"2026-07-05T09:10:45.077382+00:00"},{"alias_kind":"pith_short_8","alias_value":"OICWVFXJ","created_at":"2026-07-05T09:10:45.077382+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15525","citing_title":"Generalized Back-Stepping Experience Replay in Sparse-Reward Environments","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5","json":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5.json","graph_json":"https://pith.science/api/pith-number/OICWVFXJLHAXVYWTZ6NUT3LOR5/graph.json","events_json":"https://pith.science/api/pith-number/OICWVFXJLHAXVYWTZ6NUT3LOR5/events.json","paper":"https://pith.science/paper/OICWVFXJ"},"agent_actions":{"view_html":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5","download_json":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5.json","view_paper":"https://pith.science/paper/OICWVFXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.11372&json=true","fetch_graph":"https://pith.science/api/pith-number/OICWVFXJLHAXVYWTZ6NUT3LOR5/graph.json","fetch_events":"https://pith.science/api/pith-number/OICWVFXJLHAXVYWTZ6NUT3LOR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5/action/storage_attestation","attest_author":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5/action/author_attestation","sign_citation":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5/action/citation_signature","submit_replication":"https://pith.science/pith/OICWVFXJLHAXVYWTZ6NUT3LOR5/action/replication_record"}},"created_at":"2026-07-05T09:10:45.077382+00:00","updated_at":"2026-07-05T09:10:45.077382+00:00"}