{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R4MA2TS7BDXK2DMUVM6QG5JR4W","short_pith_number":"pith:R4MA2TS7","schema_version":"1.0","canonical_sha256":"8f180d4e5f08eead0d94ab3d037531e5ad5d903f3dcfdfdd861844047ba68186","source":{"kind":"arxiv","id":"2305.18633","version":1},"attestation_state":"computed","paper":{"title":"Experience Filter: Using Past Experiences on Unseen Tasks or Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Anil Yildiz, Anthony L. Corso, Esen Yel, Kyle H. Wray, Mykel J. Kochenderfer, Stefan J. Witwicki","submitted_at":"2023-05-29T21:57:06Z","abstract_excerpt":"One of the bottlenecks of training autonomous vehicle (AV) agents is the variability of training environments. Since learning optimal policies for unseen environments is often very costly and requires substantial data collection, it becomes computationally intractable to train the agent on every possible environment or task the AV may encounter. This paper introduces a zero-shot filtering approach to interpolate learned policies of past experiences to generalize to unseen ones. We use an experience kernel to correlate environments. These correlations are then exploited to produce policies for "},"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":"2305.18633","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-05-29T21:57:06Z","cross_cats_sorted":[],"title_canon_sha256":"f8fc0e50ddc1c306b78c2e1edf2288230e203030d0a681bbfdebb208efb3e78c","abstract_canon_sha256":"986cc5dae0b77c60a995eda8ed5a1d29f4dab00bd1056449add8428e19fd94ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:03.123303Z","signature_b64":"xXPi3/UQg9TDcnubLYxBxXljZ1dQMsmrf9M0nX+WmCev2uAD8alwQLY4UuqvQFDrrrwb2zJuZDz1rM97PLS4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f180d4e5f08eead0d94ab3d037531e5ad5d903f3dcfdfdd861844047ba68186","last_reissued_at":"2026-07-05T06:15:03.122817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:03.122817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Experience Filter: Using Past Experiences on Unseen Tasks or Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Anil Yildiz, Anthony L. Corso, Esen Yel, Kyle H. Wray, Mykel J. Kochenderfer, Stefan J. Witwicki","submitted_at":"2023-05-29T21:57:06Z","abstract_excerpt":"One of the bottlenecks of training autonomous vehicle (AV) agents is the variability of training environments. Since learning optimal policies for unseen environments is often very costly and requires substantial data collection, it becomes computationally intractable to train the agent on every possible environment or task the AV may encounter. This paper introduces a zero-shot filtering approach to interpolate learned policies of past experiences to generalize to unseen ones. We use an experience kernel to correlate environments. These correlations are then exploited to produce policies for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18633","kind":"arxiv","version":1},"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/2305.18633/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":"2305.18633","created_at":"2026-07-05T06:15:03.122875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18633v1","created_at":"2026-07-05T06:15:03.122875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18633","created_at":"2026-07-05T06:15:03.122875+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4MA2TS7BDXK","created_at":"2026-07-05T06:15:03.122875+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4MA2TS7BDXK2DMU","created_at":"2026-07-05T06:15:03.122875+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4MA2TS7","created_at":"2026-07-05T06:15:03.122875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4MA2TS7BDXK2DMUVM6QG5JR4W","json":"https://pith.science/pith/R4MA2TS7BDXK2DMUVM6QG5JR4W.json","graph_json":"https://pith.science/api/pith-number/R4MA2TS7BDXK2DMUVM6QG5JR4W/graph.json","events_json":"https://pith.science/api/pith-number/R4MA2TS7BDXK2DMUVM6QG5JR4W/events.json","paper":"https://pith.science/paper/R4MA2TS7"},"agent_actions":{"view_html":"https://pith.science/pith/R4MA2TS7BDXK2DMUVM6QG5JR4W","download_json":"https://pith.science/pith/R4MA2TS7BDXK2DMUVM6QG5JR4W.json","view_paper":"https://pith.science/paper/R4MA2TS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18633&json=true","fetch_graph":"https://pith.science/api/pith-number/R4MA2TS7BDXK2DMUVM6QG5JR4W/graph.json","fetch_events":"https://pith.science/api/pith-number/R4MA2TS7BDXK2DMUVM6QG5JR4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4MA2TS7BDXK2DMUVM6QG5JR4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4MA2TS7BDXK2DMUVM6QG5JR4W/action/storage_attestation","attest_author":"https://pith.science/pith/R4MA2TS7BDXK2DMUVM6QG5JR4W/action/author_attestation","sign_citation":"https://pith.science/pith/R4MA2TS7BDXK2DMUVM6QG5JR4W/action/citation_signature","submit_replication":"https://pith.science/pith/R4MA2TS7BDXK2DMUVM6QG5JR4W/action/replication_record"}},"created_at":"2026-07-05T06:15:03.122875+00:00","updated_at":"2026-07-05T06:15:03.122875+00:00"}