{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4VQ4HAWWZO25SPSDCXFQBYX6YR","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":"fb61cf8b9e60193ba7b6ea6dca9c40299dcf39e8c95fd4c1ab57a62204bd0ca1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-15T16:01:21Z","title_canon_sha256":"d5636edc6a7cbe6e5e20f05e927811d5bc45ebc5ed78bb176739d14f5933154e"},"schema_version":"1.0","source":{"id":"2505.10442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10442","created_at":"2026-07-05T11:03:38Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10442v1","created_at":"2026-07-05T11:03:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10442","created_at":"2026-07-05T11:03:38Z"},{"alias_kind":"pith_short_12","alias_value":"4VQ4HAWWZO25","created_at":"2026-07-05T11:03:38Z"},{"alias_kind":"pith_short_16","alias_value":"4VQ4HAWWZO25SPSD","created_at":"2026-07-05T11:03:38Z"},{"alias_kind":"pith_short_8","alias_value":"4VQ4HAWW","created_at":"2026-07-05T11:03:38Z"}],"graph_snapshots":[{"event_id":"sha256:98bd8815f6667c3ae9e9ac7fd96951d9793eb12e6712c3ebf4968ad31648d56f","target":"graph","created_at":"2026-07-05T11:03:38Z","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/2505.10442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation learning (IL) and reinforcement learning (RL) each offer distinct advantages for robotics policy learning: IL provides stable learning from demonstrations, and RL promotes generalization through exploration. While existing robot learning approaches using IL-based pre-training followed by RL-based fine-tuning are promising, this two-step learning paradigm often suffers from instability and poor sample efficiency during the RL fine-tuning phase. In this work, we introduce IN-RIL, INterleaved Reinforcement learning and Imitation Learning, for policy fine-tuning, which periodically injec","authors_text":"Ahmadreza Moradipari, Dechen Gao, Hanchu Zhou, Hang Wang, Iman Soltani, Junshan Zhang, Nejib Ammar, Shatadal Mishra","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-15T16:01:21Z","title":"IN-RIL: Interleaved Reinforcement and Imitation Learning for Policy Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10442","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":"sha256:1681d714c7ad8da7a0cedd2fe1e7b48020a8da42a89af9e2041f6e0db9118bce","target":"record","created_at":"2026-07-05T11:03:38Z","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":"fb61cf8b9e60193ba7b6ea6dca9c40299dcf39e8c95fd4c1ab57a62204bd0ca1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-15T16:01:21Z","title_canon_sha256":"d5636edc6a7cbe6e5e20f05e927811d5bc45ebc5ed78bb176739d14f5933154e"},"schema_version":"1.0","source":{"id":"2505.10442","kind":"arxiv","version":1}},"canonical_sha256":"e561c382d6cbb5d93e4315cb00e2fec446f3617a04d8e7ac5b6da134156e0a0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e561c382d6cbb5d93e4315cb00e2fec446f3617a04d8e7ac5b6da134156e0a0e","first_computed_at":"2026-07-05T11:03:38.419260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:38.419260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jdJX7X8NYjkonkbdCvj6I+1PYV5Tux/209KQnshwzawrDS85XKzZq6yAHF8sXrPYsQctT4p4hQGaNQg4rBdeBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:38.419703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1681d714c7ad8da7a0cedd2fe1e7b48020a8da42a89af9e2041f6e0db9118bce","sha256:98bd8815f6667c3ae9e9ac7fd96951d9793eb12e6712c3ebf4968ad31648d56f"],"state_sha256":"bc0929681dd998efac9625159b877334733a4e3d04d8fbe33b14296c6b4f5fb2"}