{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:DWN6HTEF2H7BB2MZUCEQWJNX6H","short_pith_number":"pith:DWN6HTEF","canonical_record":{"source":{"id":"1406.5979","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-23T17:00:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d2a973a8917376ff45ba850aba10203e6a35e4a73c5b1435ebaf46ce82c80f8d","abstract_canon_sha256":"773da57c646aecc83fceade487abd5c97e02a078e76483ddc1082821dadbf790"},"schema_version":"1.0"},"canonical_sha256":"1d9be3cc85d1fe10e999a0890b25b7f1c4b149450c07e23ac736e4be2ade9070","source":{"kind":"arxiv","id":"1406.5979","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.5979","created_at":"2026-05-18T02:49:10Z"},{"alias_kind":"arxiv_version","alias_value":"1406.5979v1","created_at":"2026-05-18T02:49:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.5979","created_at":"2026-05-18T02:49:10Z"},{"alias_kind":"pith_short_12","alias_value":"DWN6HTEF2H7B","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"DWN6HTEF2H7BB2MZ","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"DWN6HTEF","created_at":"2026-05-18T12:28:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:DWN6HTEF2H7BB2MZUCEQWJNX6H","target":"record","payload":{"canonical_record":{"source":{"id":"1406.5979","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-23T17:00:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d2a973a8917376ff45ba850aba10203e6a35e4a73c5b1435ebaf46ce82c80f8d","abstract_canon_sha256":"773da57c646aecc83fceade487abd5c97e02a078e76483ddc1082821dadbf790"},"schema_version":"1.0"},"canonical_sha256":"1d9be3cc85d1fe10e999a0890b25b7f1c4b149450c07e23ac736e4be2ade9070","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:49:10.372390Z","signature_b64":"/yGfGxyNEAhWcpHX3uiiif4Lp6o1PAg/L57JV+RqhfI2aFeeKuc8Vg7QrOVFVDPk+sORpqfjCP7/quPJqQuRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d9be3cc85d1fe10e999a0890b25b7f1c4b149450c07e23ac736e4be2ade9070","last_reissued_at":"2026-05-18T02:49:10.371959Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:49:10.371959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1406.5979","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:49:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GOeONsqxq8dM+4gBBAl7UpoY4uZKFUAXKNDG1prYJpfqiuEDJHTMTUXN6sE5iP1V8lvxS2KyszH7W1A/+DcADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T04:41:05.632730Z"},"content_sha256":"c02dc4a541e243c31a31309364d2ef46a82077b005f924a08253a3c0f32afb4a","schema_version":"1.0","event_id":"sha256:c02dc4a541e243c31a31309364d2ef46a82077b005f924a08253a3c0f32afb4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:DWN6HTEF2H7BB2MZUCEQWJNX6H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement and Imitation Learning via Interactive No-Regret Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"J. Andrew Bagnell, Stephane Ross","submitted_at":"2014-06-23T17:00:28Z","abstract_excerpt":"Recent work has demonstrated that problems-- particularly imitation learning and structured prediction-- where a learner's predictions influence the input-distribution it is tested on can be naturally addressed by an interactive approach and analyzed using no-regret online learning. These approaches to imitation learning, however, neither require nor benefit from information about the cost of actions. We extend existing results in two directions: first, we develop an interactive imitation learning approach that leverages cost information; second, we extend the technique to address reinforcemen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.5979","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:49:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nnCWqa6KRD9RLrKpcL5wQeC6k9LfyjdENSDz92LCo3A5fecd1WXLVjUIa2lUkudZ/roWr0cfxrk2bZNnM+lCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T04:41:05.633088Z"},"content_sha256":"37961411570750585b01e533a6ec5345aeec3ac4197b189fd87a0332d2d646cc","schema_version":"1.0","event_id":"sha256:37961411570750585b01e533a6ec5345aeec3ac4197b189fd87a0332d2d646cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DWN6HTEF2H7BB2MZUCEQWJNX6H/bundle.json","state_url":"https://pith.science/pith/DWN6HTEF2H7BB2MZUCEQWJNX6H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DWN6HTEF2H7BB2MZUCEQWJNX6H/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-22T04:41:05Z","links":{"resolver":"https://pith.science/pith/DWN6HTEF2H7BB2MZUCEQWJNX6H","bundle":"https://pith.science/pith/DWN6HTEF2H7BB2MZUCEQWJNX6H/bundle.json","state":"https://pith.science/pith/DWN6HTEF2H7BB2MZUCEQWJNX6H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DWN6HTEF2H7BB2MZUCEQWJNX6H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:DWN6HTEF2H7BB2MZUCEQWJNX6H","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":"773da57c646aecc83fceade487abd5c97e02a078e76483ddc1082821dadbf790","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-23T17:00:28Z","title_canon_sha256":"d2a973a8917376ff45ba850aba10203e6a35e4a73c5b1435ebaf46ce82c80f8d"},"schema_version":"1.0","source":{"id":"1406.5979","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.5979","created_at":"2026-05-18T02:49:10Z"},{"alias_kind":"arxiv_version","alias_value":"1406.5979v1","created_at":"2026-05-18T02:49:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.5979","created_at":"2026-05-18T02:49:10Z"},{"alias_kind":"pith_short_12","alias_value":"DWN6HTEF2H7B","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"DWN6HTEF2H7BB2MZ","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"DWN6HTEF","created_at":"2026-05-18T12:28:25Z"}],"graph_snapshots":[{"event_id":"sha256:37961411570750585b01e533a6ec5345aeec3ac4197b189fd87a0332d2d646cc","target":"graph","created_at":"2026-05-18T02:49:10Z","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"},"paper":{"abstract_excerpt":"Recent work has demonstrated that problems-- particularly imitation learning and structured prediction-- where a learner's predictions influence the input-distribution it is tested on can be naturally addressed by an interactive approach and analyzed using no-regret online learning. These approaches to imitation learning, however, neither require nor benefit from information about the cost of actions. We extend existing results in two directions: first, we develop an interactive imitation learning approach that leverages cost information; second, we extend the technique to address reinforcemen","authors_text":"J. Andrew Bagnell, Stephane Ross","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-23T17:00:28Z","title":"Reinforcement and Imitation Learning via Interactive No-Regret Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.5979","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:c02dc4a541e243c31a31309364d2ef46a82077b005f924a08253a3c0f32afb4a","target":"record","created_at":"2026-05-18T02:49:10Z","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":"773da57c646aecc83fceade487abd5c97e02a078e76483ddc1082821dadbf790","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-23T17:00:28Z","title_canon_sha256":"d2a973a8917376ff45ba850aba10203e6a35e4a73c5b1435ebaf46ce82c80f8d"},"schema_version":"1.0","source":{"id":"1406.5979","kind":"arxiv","version":1}},"canonical_sha256":"1d9be3cc85d1fe10e999a0890b25b7f1c4b149450c07e23ac736e4be2ade9070","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d9be3cc85d1fe10e999a0890b25b7f1c4b149450c07e23ac736e4be2ade9070","first_computed_at":"2026-05-18T02:49:10.371959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:49:10.371959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/yGfGxyNEAhWcpHX3uiiif4Lp6o1PAg/L57JV+RqhfI2aFeeKuc8Vg7QrOVFVDPk+sORpqfjCP7/quPJqQuRCw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:49:10.372390Z","signed_message":"canonical_sha256_bytes"},"source_id":"1406.5979","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c02dc4a541e243c31a31309364d2ef46a82077b005f924a08253a3c0f32afb4a","sha256:37961411570750585b01e533a6ec5345aeec3ac4197b189fd87a0332d2d646cc"],"state_sha256":"0d8388db90fb4038f2d7abde0631cc919a1c2e7f38174461547829d0489467ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pVv9eG39n/4toB+y3TypqL4t2gM5TRRNS24hmCvi0Fv1vQr4lXInqmPKGJT5cz8N3wa3ZU8UzRBP3W7gbWAmDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T04:41:05.636177Z","bundle_sha256":"6b61d531a45b43238e9b45d048f546433634b7fd313c710e6335050d01b1f3fb"}}