{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GG5YYAOINE4ZQZCMOTO2C333NI","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":"c7ef6e6cb98af77687c0db8297350e7a85b37a08e42386556052cf35cf483528","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-29T22:44:59Z","title_canon_sha256":"3baf3b028516bae5321f2d1e2a9b6ad45f00dd106d9f0c232f51288a540bdbfc"},"schema_version":"1.0","source":{"id":"1909.13392","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.13392","created_at":"2026-07-05T00:08:09Z"},{"alias_kind":"arxiv_version","alias_value":"1909.13392v1","created_at":"2026-07-05T00:08:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.13392","created_at":"2026-07-05T00:08:09Z"},{"alias_kind":"pith_short_12","alias_value":"GG5YYAOINE4Z","created_at":"2026-07-05T00:08:09Z"},{"alias_kind":"pith_short_16","alias_value":"GG5YYAOINE4ZQZCM","created_at":"2026-07-05T00:08:09Z"},{"alias_kind":"pith_short_8","alias_value":"GG5YYAOI","created_at":"2026-07-05T00:08:09Z"}],"graph_snapshots":[{"event_id":"sha256:899f846908701cffcc014a9dc9abb784c75028a4f115d1c66289d131d9e45b11","target":"graph","created_at":"2026-07-05T00:08:09Z","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/1909.13392/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a method for learning from video demonstrations by using human feedback to construct a mapping between the standard representation of the agent and the visual representation of the demonstration. In this way, we leverage the advantages of both these representations, i.e., we learn the policy using standard state representations, but are able to specify the expected behavior using video demonstration. We train an autonomous agent using a single video demonstration and use human feedback (using numerical similarity rating) to map the standard representation to the visua","authors_text":"Nicholas Waytowich, Sunil Gandhi, Tim Oates, Tinoosh Mohsenin","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-29T22:44:59Z","title":"Learning from Observations Using a Single Video Demonstration and Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.13392","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":"sha256:08bd1702afd16ffc63d19b93ac8df3665d22b48c2116b854cbd60c7b6cd3b34f","target":"record","created_at":"2026-07-05T00:08:09Z","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":"c7ef6e6cb98af77687c0db8297350e7a85b37a08e42386556052cf35cf483528","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-29T22:44:59Z","title_canon_sha256":"3baf3b028516bae5321f2d1e2a9b6ad45f00dd106d9f0c232f51288a540bdbfc"},"schema_version":"1.0","source":{"id":"1909.13392","kind":"arxiv","version":1}},"canonical_sha256":"31bb8c01c8693998644c74dda16f7b6a1e7d9fc007576cd7178fb9a1cfc1312c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31bb8c01c8693998644c74dda16f7b6a1e7d9fc007576cd7178fb9a1cfc1312c","first_computed_at":"2026-07-05T00:08:09.867941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:08:09.867941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EWs4lmJuKsMw6OoNNoxb5h9Ol3jEuplDQz74Z0fxtRg4e6etSuo8slwMKuVFLm7zzAdsjYdEbD9gTZhSMw7cBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:08:09.868428Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.13392","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08bd1702afd16ffc63d19b93ac8df3665d22b48c2116b854cbd60c7b6cd3b34f","sha256:899f846908701cffcc014a9dc9abb784c75028a4f115d1c66289d131d9e45b11"],"state_sha256":"d6c91bb145b524019f17eca406e38bd96c44999081873543ed9015f04b5c0bcd"}