{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CZRBCAAIN3TQS2JTTW7HSJRCVI","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":"00125792be56f1ad7ca55977a25c9f96dbef0ab7b9fc789185c3244549d7c75e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-06-18T19:07:41Z","title_canon_sha256":"381f63b78d4e67917815a61104546753b19ffb80f3c5f8b28a65dc823fcf21bc"},"schema_version":"1.0","source":{"id":"2106.10318","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.10318","created_at":"2026-07-05T02:50:48Z"},{"alias_kind":"arxiv_version","alias_value":"2106.10318v1","created_at":"2026-07-05T02:50:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10318","created_at":"2026-07-05T02:50:48Z"},{"alias_kind":"pith_short_12","alias_value":"CZRBCAAIN3TQ","created_at":"2026-07-05T02:50:48Z"},{"alias_kind":"pith_short_16","alias_value":"CZRBCAAIN3TQS2JT","created_at":"2026-07-05T02:50:48Z"},{"alias_kind":"pith_short_8","alias_value":"CZRBCAAI","created_at":"2026-07-05T02:50:48Z"}],"graph_snapshots":[{"event_id":"sha256:0952b60c06489ffa342c516abef8b94ed68e064b0c2415fddf1004de159c3d82","target":"graph","created_at":"2026-07-05T02:50:48Z","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/2106.10318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present an algorithm to efficiently learn socially-compliant navigation policies from observations of human trajectories. As mobile robots come to inhabit and traffic social spaces, they must account for social cues and behave in a socially compliant manner. We focus on learning such cues from examples. We describe an inverse reinforcement learning based algorithm which learns from human trajectory observations without knowing their specific actions. We increase the sample-efficiency of our approach over alternative methods by leveraging the notion of a replay buffer (found i","authors_text":"Bobak H. Baghi, Gregory Dudek","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-06-18T19:07:41Z","title":"Sample Efficient Social Navigation Using Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10318","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":"sha256:0514a55a4d1ab8a382362aabd2a852a4de79753ca7a86dece3203da961f2a749","target":"record","created_at":"2026-07-05T02:50:48Z","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":"00125792be56f1ad7ca55977a25c9f96dbef0ab7b9fc789185c3244549d7c75e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-06-18T19:07:41Z","title_canon_sha256":"381f63b78d4e67917815a61104546753b19ffb80f3c5f8b28a65dc823fcf21bc"},"schema_version":"1.0","source":{"id":"2106.10318","kind":"arxiv","version":1}},"canonical_sha256":"16621100086ee70969339dbe792622aa27234a1dc20a9a12962fa15783699b69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16621100086ee70969339dbe792622aa27234a1dc20a9a12962fa15783699b69","first_computed_at":"2026-07-05T02:50:48.507759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:48.507759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MHjNY/DG6Ml8zrFULjWhHWHFsbAQmptZiBIYCPOdHSHHcDpLISq7D7azeK1AlkLpodNfs1yEIpxxyc9BeK/gDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:48.508346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.10318","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0514a55a4d1ab8a382362aabd2a852a4de79753ca7a86dece3203da961f2a749","sha256:0952b60c06489ffa342c516abef8b94ed68e064b0c2415fddf1004de159c3d82"],"state_sha256":"6b9ba2d11b6460da819f0b11485dcaed0ba4292d608d9c81b5356307964a954e"}